diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index 7b95401dc46245ac339fc25059d4a56d90b4cde5..ad110341d34c906b25400d0e37503291ee6dffd5 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,45 @@ --- license: apache-2.0 +language: +- en +- de +- es +- fr +- it +- pt +- pl +- nl +- tr +- sv +- cs +- el +- hu +- ro +- fi +- uk +- sl +- sk +- da +- lt +- lv +- et +- bg +- 'no' +- ca +- hr +- ga +- mt +- gl +- zh +- ru +- ko +- ja +- ar +- hi +base_model: NousResearch/Hermes-3-Llama-3.1-8B +base_model_relation: quantized +library_name: mlc-llm +pipeline_tag: text-generation --- + +4-bit [GPTQ](https://arxiv.org/abs/2210.17323) quantized version of [utter-project/EuroLLM-9B-Instruct](https://huggingface.co/utter-project/EuroLLM-9B-Instruct) for inference with the [Private LLM](https://privatellm.app/) app. diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..1997fb2e09625d2187f767b9f1643dda7fa236f3 --- /dev/null +++ b/config.json @@ -0,0 +1,6 @@ +{ + "quantization_config": { + "bits": 4 + } +} + diff --git a/ndarray-cache.json b/ndarray-cache.json new file mode 100644 index 0000000000000000000000000000000000000000..1abf54dfae3d4acfcd9dc635a28f7f1e7dd03a06 --- /dev/null +++ b/ndarray-cache.json @@ -0,0 +1,5623 @@ +{ + "metadata": { + "ParamSize": 425, + "ParamBytes": 4719681536.0, + "BitsPerParam": 3.2403624459229405 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 262144000, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 512, + 128000 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 262144000, + "byteOffset": 0 + } + ], + "md5sum": "f24aaa6056ecbff2352411223821b309" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 33366016, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 32, + 128000 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192000, + "byteOffset": 0 + }, + { + "name": "model.layers.36.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 8192000 + }, + { + "name": "model.layers.36.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 8200192 + } + ], + "md5sum": "c42612875deb70a36ee1367c77b10553" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "d0868656246d4fe7cff4bd5884d6daf4" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.37.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "d79ccfa535799db26eecf62045d1d08b" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "f9e95aa5063ffe2d3bf51c638dd7b139" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 26370048, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 0 + }, + { + "name": "model.layers.36.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 786432 + }, + { + "name": "model.layers.36.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 2359296 + }, + { + "name": "model.layers.36.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 2367488 + }, + { + "name": "model.layers.36.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 14950400 + }, + { + "name": "model.layers.36.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 15343616 + }, + { + "name": "model.layers.36.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 23732224 + }, + { + "name": "model.layers.37.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + }, + { + "name": "model.layers.37.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 24002560 + }, + { + "name": "model.layers.37.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 24788992 + }, + { + "name": "model.layers.37.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 26361856 + } + ], + "md5sum": "9a968cfe4b4f1578bdaaad0034c0c81e" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "da6d1509f91e9052c6b64d3afbd3ca17" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "f92deafc55d26a8e65f2f5588476cc72" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.37.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.37.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.37.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.37.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.38.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.38.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.38.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.38.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "824c6cc6b5401036b2daf9696c4034ea" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.39.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "a2b00c285227cb1f17b40f47c9d32cd4" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "bcd53c79c167060c4666e56d7a9442b2" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.38.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.38.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.38.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.38.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.39.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.39.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.39.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.39.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "b8e7d32b24a9e2e8045429809fecd310" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.40.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "228620e958e9020bc26db3b16fb5b551" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.40.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "356056454133aa7a65a53b186e8be788" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.39.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.39.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.39.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.39.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.40.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.40.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.40.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.40.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "cbb374ed85bfd3a57cbde7305ee5df81" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.41.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "594e80b7b9da7c03e83ae9e81f457447" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "2389fd72c754fe5856237898a9aa3060" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.40.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.40.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.40.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.40.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.41.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.41.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.41.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.41.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "d56109a95b5564c5a4bf2968b3a43ae3" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 262144000, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 128000, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 262144000, + "byteOffset": 0 + } + ], + "md5sum": "5cb0046e415bebcd14104c5d33a28339" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "60b82c859eb00072e5cfecd731856387" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "be93c66b9073a1c6b5053155db389f84" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 32202752, + "records": [ + { + "name": "model.layers.41.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.41.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.41.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.41.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.norm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 128000, + 32 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192000, + "byteOffset": 21635072 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 29827072 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 29835264 + }, + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 30621696 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 32194560 + } + ], + "md5sum": "5f76625d38056ce3ef595b08b3548dd1" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "7d1c82479b08bc86bea471818854ed25" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "d06d42d0ccf470ad9c0894bb52d55107" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "3d0bfc811ff0fbb8067e23eadbee3bd3" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 21626880, + "records": [ + { + "name": "model.layers.1.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + } + ], + "md5sum": "e9d0bdab741b0ab18a174f8c5d10390c" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "aa8aa6c92292cb03dd0329c99842d211" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "75ee28e586317a92b68071868486935d" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "21337f4376d5ce4614e18b06de582110" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "3a48b23f609c1bcf3ffcf31d67176e1b" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "906795adb932dcf9b5f31965739470b7" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "03a70ecb5d94b57f160b71a88bab86d7" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "5964a661f94059a66148564bf0550ce5" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "6b2268fde1bbb61c2c7957d922d12b9c" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "35c8924776a7b8952552924101672092" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "9d7dc5e1a6a87c3249469aabc9f029b7" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "7c7ba3a87dbe1f4763ab22c2fb801236" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "e1f63f06b17b2aaf99bc1842cae58365" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "ba134edbef6dd31652647eb63ba97074" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "9894fd6688cc187aa71648e8d602b0ae" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "55b68d6a448004a80757b3b80f513f4a" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "b2a827c352064fe9f66e0fc5f6879aab" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "3babd907489aa599715e79bdcc2cb6f6" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "68c95afe32cabd902a66af1ecf6609b2" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "f2946167eb7384712e88143076cae79f" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "812601870bfd928d9aeb203efcded6f2" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "8fe544da2e3f10b7851725586003c28b" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "d21880451647fa1431623091f92569e0" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "1fb6a74335709301f4422787547c3ad8" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "de551d55089196be3fe1ad3e3208a8f5" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "201676c3f48794ec0f8090677bbf1412" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "4949dcc07a4ccad9a297613f27de0a47" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "2d9f6764707e27653d24a840d93517ad" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "7800438dd0bd2eaa7b2828a08a123965" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 26378240, + "records": [ + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24002560 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 24010752 + }, + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 24797184 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 26370048 + } + ], + "md5sum": "17a115872f8d97c7e8349b6c25cb13ef" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "cb97096ffd384b8ec26b574401a9d6e8" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "357160b9165a1e2aec38cb2dd50906b4" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "906a23c93568b61fc5bf871a3467e2aa" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "c20f2aaca668538639af304306fac88b" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "13e185a7dbdc506ea5beab5c5ca1b660" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "da6b8914e3e5d0521657f782a3edb267" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "9e996f7c627ac8ad626145904b13a77e" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "bc5d0c7c49a7b5bf90aa024bcea8fea0" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "1e0664d7102580f1ce81171845934879" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "eceda4e63ae94d3b2dd7f8dba8d5db5a" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "dcb9c96e2e6a56c16e5d7253d810d7e6" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "16d0d602532313d638879049568dec67" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "676de2bb13313916ab8acb1191646f3b" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "c40f6f1cd508735352c6e3379bbe471d" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "94c5b51d675a0cc10fee598d3e331a3c" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "e2906a503e257dc08cdbd1bf15e46b1c" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "a91eb53aaddbe63c69b9eb80f8e63aca" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "3ac3ea6d299c28fa50286cbfbc21d8a5" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "e714db2d47cbaada663e6668d38cad67" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "d9bca83ae0bb51a3d8e8d13e2d446f79" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "f67c9dabcde3c1277f4b8025fa0b90c0" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "a46995e85015d027e05cbbd5745ed187" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "a30888e8807043195628ec4c8c924ae6" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "103456b28c13608658dc746de2a6c747" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "d3312f9a759b5bade7a91e71fd6b6227" + }, + { + "dataPath": "params_shard_80.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "29d6a7f9f0c360249b5c4301dc309c48" + }, + { + "dataPath": "params_shard_81.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "644a169d139b9ef354720c970fd5b257" + }, + { + "dataPath": "params_shard_82.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "d76bbe0b7abf42828af086a3ecada8f3" + }, + { + "dataPath": "params_shard_83.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "8694d98f9a18fb0fa92c4beae4e66e4f" + }, + { + "dataPath": "params_shard_84.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "c2c9c70e5fd297e2429d5a24aa9c4206" + }, + { + "dataPath": "params_shard_85.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "4d9cb56add994bf5a7a997ab80789234" + }, + { + "dataPath": "params_shard_86.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "d598bf69a0588531dd992bab6b81f3a2" + }, + { + "dataPath": "params_shard_87.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "2e22a9b4b2d7c6d533f924c15ebc6407" + }, + { + "dataPath": "params_shard_88.bin", + "format": "raw-shard", + "nbytes": 21626880, + "records": [ + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + } + ], + "md5sum": "a64d473c7648f064258e2074aa0a8242" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "ce7e9783b1f212a8d023fc4b679f4429" + }, + { + "dataPath": "params_shard_90.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "5af5e6c16815dc064fdb0a6b8f36510b" + }, + { + "dataPath": "params_shard_91.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "2b729d52852327a8767ca04ed7cd0faf" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "c586da95f83550a2bc557ad6f7cd93d6" + }, + { + "dataPath": "params_shard_93.bin", + "format": "raw-shard", + "nbytes": 26378240, + "records": [ + { + "name": "model.layers.23.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 12976128 + }, + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12984320 + }, + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 13770752 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 15343616 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 15351808 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 23740416 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24002560 + }, + { + "name": "model.layers.24.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 24010752 + }, + { + "name": "model.layers.24.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 24797184 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 26370048 + } + ], + "md5sum": "fd943cc5c7ed2c1e79f84ced4f847580" + }, + { + "dataPath": "params_shard_94.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "d386547e760a06ad1fafbc6a2ea8a8b8" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "f57868f389b2d7bb61c76bc51f665043" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.24.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.25.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.25.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "4c4fecfc74c23d8c6457a9d4bdf8b16b" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.26.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "fa40eb66b8880d0737f03bd70dabe584" + }, + { + "dataPath": "params_shard_98.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "df208ff582f68f751f8f69bdbadb5816" + }, + { + "dataPath": "params_shard_99.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.25.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.26.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.26.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "a2c946b4cee44dd84eba94640aaed41d" + }, + { + "dataPath": "params_shard_100.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "67829fea653e46bd380d334f6b28d786" + }, + { + "dataPath": "params_shard_101.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "81272f36765c1a8249b55c1bd4645afe" + }, + { + "dataPath": "params_shard_102.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.26.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.27.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.27.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "167c37963f94af725cabe62b0f5e4c35" + }, + { + "dataPath": "params_shard_103.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "225fcd59a886f5ac5e6e909300767dc8" + }, + { + "dataPath": "params_shard_104.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "2b56c29aef76a3f9fc85ced480991090" + }, + { + "dataPath": "params_shard_105.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.27.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.28.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.28.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.28.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.28.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "46113190c3807506f2815bbf7cf22633" + }, + { + "dataPath": "params_shard_106.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "5b04909925bc636aa0b684d9d869312c" + }, + { + "dataPath": "params_shard_107.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "b506044ea14cddb3951b1cec99c7ac33" + }, + { + "dataPath": "params_shard_108.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.28.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.29.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.29.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.29.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.29.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "ae1247434d26a8a20f251987402fb7ef" + }, + { + "dataPath": "params_shard_109.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.30.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "b026f375987e57fb1ce191fee3eadd7b" + }, + { + "dataPath": "params_shard_110.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "8278e0adc8077b0a3c4cc1cfb0f86a30" + }, + { + "dataPath": "params_shard_111.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.29.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.29.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.29.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.30.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.30.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.30.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "2ccf198b447efb649c3cd884f411fea9" + }, + { + "dataPath": "params_shard_112.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "a8377f50b8e5eb61e9918686875cbbaa" + }, + { + "dataPath": "params_shard_113.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "b44fd7a72076e86dfa296faa080c212e" + }, + { + "dataPath": "params_shard_114.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.30.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.31.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.31.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "a522b66345ce26d85829e2d8995f1056" + }, + { + "dataPath": "params_shard_115.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "cb877782104828540268792016988d0e" + }, + { + "dataPath": "params_shard_116.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.32.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "715339be4fd3e72bd09e89a0a7a0d715" + }, + { + "dataPath": "params_shard_117.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.31.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.31.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.32.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.32.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.32.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.32.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "c68ec24ec9e3604fc0318dcf587c07fe" + }, + { + "dataPath": "params_shard_118.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.33.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "431575ae4c02ef717193cd6607e1811e" + }, + { + "dataPath": "params_shard_119.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "0b3f2afc6d45316cd4b8875db1e24ba9" + }, + { + "dataPath": "params_shard_120.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.32.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.32.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.32.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.32.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.33.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.33.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.33.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.33.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "a9e8ca66227ca7d87c718e53ca225d67" + }, + { + "dataPath": "params_shard_121.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "27b160af5088f849824236a7a0d6a4ce" + }, + { + "dataPath": "params_shard_122.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "044cfad26346705bde336c9356ef6d65" + }, + { + "dataPath": "params_shard_123.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.33.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.33.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.33.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.33.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.34.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.34.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.34.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.34.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "95f532e34ac814f7044bc1c235cf584e" + }, + { + "dataPath": "params_shard_124.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.35.mlp.down_proj.q_weight", + "shape": [ + 1536, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "bd40caeb468a325d4c992161bc72a73c" + }, + { + "dataPath": "params_shard_125.bin", + "format": "raw-shard", + "nbytes": 50331648, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_weight", + "shape": [ + 512, + 24576 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 50331648, + "byteOffset": 0 + } + ], + "md5sum": "a317be74fb52857a9dd2aa1dbea3783d" + }, + { + "dataPath": "params_shard_126.bin", + "format": "raw-shard", + "nbytes": 24002560, + "records": [ + { + "name": "model.layers.34.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.34.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.34.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.34.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + }, + { + "name": "model.layers.35.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21626880 + }, + { + "name": "model.layers.35.mlp.down_proj.q_scale", + "shape": [ + 96, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 21635072 + }, + { + "name": "model.layers.35.mlp.gate_up_proj.q_scale", + "shape": [ + 32, + 24576 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1572864, + "byteOffset": 22421504 + }, + { + "name": "model.layers.35.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 23994368 + } + ], + "md5sum": "1992f20cfa253393207fa4fe85acee18" + }, + { + "dataPath": "params_shard_127.bin", + "format": "raw-shard", + "nbytes": 21626880, + "records": [ + { + "name": "model.layers.35.self_attn.qkv_proj.q_weight", + "shape": [ + 512, + 6144 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.35.self_attn.qkv_proj.q_scale", + "shape": [ + 32, + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.35.self_attn.o_proj.q_weight", + "shape": [ + 512, + 4096 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 8388608, + "byteOffset": 12976128 + }, + { + "name": "model.layers.35.self_attn.o_proj.q_scale", + "shape": [ + 32, + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21364736 + } + ], + "md5sum": "0a29195282fa3c68f4aa8dc8907da369" + } + ] +} \ No newline at end of file diff --git a/params_shard_0.bin b/params_shard_0.bin new file mode 100644 index 0000000000000000000000000000000000000000..242c4043f87d61ed76879291f2b4e1187c25a154 --- /dev/null +++ b/params_shard_0.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5165ddbab7f603d4e9eb3a83303bcb054a3f78110a9ed2af05409ba486089fbb +size 262144000 diff --git a/params_shard_1.bin b/params_shard_1.bin new file mode 100644 index 0000000000000000000000000000000000000000..46cd566536462de57272a8766e86739f59193c3a --- /dev/null +++ b/params_shard_1.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c0082ef864127a9cf8262515cdde15aa1e25f7d1eb1c20800c4e5acb13cef00 +size 33366016 diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..9295ba8f30eb1bc0e3b8da4afc3beb5d8fbdb03a --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5b6f705ad17d5a0b6761cd8e9a164c44f92f2154f671de287e77e4c21cf6bc +size 50331648 diff --git a/params_shard_100.bin b/params_shard_100.bin new file mode 100644 index 0000000000000000000000000000000000000000..ba6fe0d178fc7441bfc84a9713792055987c8e5b --- /dev/null +++ b/params_shard_100.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46029fe1ed2088363d74f29ea457788777d2638810dbf0ec1a47c406a424bd75 +size 25165824 diff --git a/params_shard_101.bin b/params_shard_101.bin new file mode 100644 index 0000000000000000000000000000000000000000..5c959e6c6c5ea289752e64aeff679612cce1abd4 --- /dev/null +++ b/params_shard_101.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aea2663ce3987fad5d69eb98863ca10819111f69636e4689a01933d589c3ca4 +size 50331648 diff --git a/params_shard_102.bin b/params_shard_102.bin new file mode 100644 index 0000000000000000000000000000000000000000..b6b00137b2b5972e6609ac0401bb3481a805deb2 --- /dev/null +++ b/params_shard_102.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:331a31116e301dc730c8d34ba15c66e5a968e6bda7af4384ed339c65ffeaf820 +size 24002560 diff --git a/params_shard_103.bin b/params_shard_103.bin new file mode 100644 index 0000000000000000000000000000000000000000..1c0b45f161d0cbfaf4b0a2a308c738613057ff07 --- /dev/null +++ b/params_shard_103.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adc629e195f20f2c41a624ad79406faa3e8aee0562304284fbdd84503e4f503a +size 25165824 diff --git a/params_shard_104.bin b/params_shard_104.bin new file mode 100644 index 0000000000000000000000000000000000000000..64699b49c91a1e494e9ece522a71d5c770cb57fd --- /dev/null +++ b/params_shard_104.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb12fc0ab8453b930c814fb60cc66cd7fccf489b01ffbeebbdcc91cdfa1e1c1 +size 50331648 diff --git a/params_shard_105.bin b/params_shard_105.bin new file mode 100644 index 0000000000000000000000000000000000000000..d8a5a55626cee2aab6641c3f7e8ff7424fa826d0 --- /dev/null +++ b/params_shard_105.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:040d0b8107064ddde748a640608fb64e6b860e2a6b89dff2393be4357b8a4677 +size 24002560 diff --git a/params_shard_106.bin b/params_shard_106.bin new file mode 100644 index 0000000000000000000000000000000000000000..fd73477489fde4a61ea5d55dfcb184ac2964edf6 --- /dev/null +++ b/params_shard_106.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4dfc333a9b8c7fc636d79a6ce5deaef7763e2cebd7bae3f176e3ad8cc93bbb2 +size 25165824 diff --git a/params_shard_107.bin b/params_shard_107.bin new file mode 100644 index 0000000000000000000000000000000000000000..699d47ed6f9b30d7c9a3cfd97a2b24a7f4deb124 --- /dev/null +++ b/params_shard_107.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce0a898a92dff10db8cdcd20eba512acc947feb0b09d9df9b754bb14594884a6 +size 50331648 diff --git a/params_shard_108.bin b/params_shard_108.bin new file mode 100644 index 0000000000000000000000000000000000000000..33562c0fb8c9bbb24701ac15602844cd48e67473 --- /dev/null +++ b/params_shard_108.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ceb818469737724a926a0741cce8e29734d3ecbb964380fdd5f8d2a5e94c2fc +size 24002560 diff --git a/params_shard_109.bin b/params_shard_109.bin new file mode 100644 index 0000000000000000000000000000000000000000..548743343600d3778d2d2677622e63fd5d2e0f1f --- /dev/null +++ b/params_shard_109.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33ed63eef426087ed86ec07498212153e434501b831acd3af0a505deaf4ff269 +size 25165824 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..7cbeb7804ddbf2cf6aab4e7b3dfa9af85a30abdb --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74952fd603bd38aab26dc85e8ebea9494b0e3c967e9e6126b0051a820ca69434 +size 24002560 diff --git a/params_shard_110.bin b/params_shard_110.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e8340bdacc6e00673935f36bf3fa10d1661adce --- /dev/null +++ b/params_shard_110.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9c1d31b5a853cd33421fe59c22a339b9b537e233d5c2c570eaa1dcf749d079a +size 50331648 diff --git a/params_shard_111.bin b/params_shard_111.bin new file mode 100644 index 0000000000000000000000000000000000000000..c317f44d76bdaee6e6841c3b444b47cdf2b3f133 --- /dev/null +++ b/params_shard_111.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b08c91d9c765f0b5943ceb2d6df9a0b1e76cbd463d0a95171c370d268639857f +size 24002560 diff --git a/params_shard_112.bin b/params_shard_112.bin new file mode 100644 index 0000000000000000000000000000000000000000..eb44ab29d6235ad6d3b87a8d5bd0a6237d69eb35 --- /dev/null +++ b/params_shard_112.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c9c8ad7e4a6e01b08404a6f25d5eae8ac169011d18aeb185b5badc4743464cd +size 25165824 diff --git a/params_shard_113.bin b/params_shard_113.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ac06c17802d1824d52d9b9ba4d12723bf591dd6 --- /dev/null +++ b/params_shard_113.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7108d56e2ad9815b0d547763dfaa07bf8b05e2166b5b2cfba5dba3adbf964e2d +size 50331648 diff --git a/params_shard_114.bin b/params_shard_114.bin new file mode 100644 index 0000000000000000000000000000000000000000..75467890e8d9877bd0df6dc79a5b031fd38bef1e --- /dev/null +++ b/params_shard_114.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b649dfdba0a5b754d06879ec34915d2c8e827ecbefbf8a80ff93aadc0d05cae +size 24002560 diff --git a/params_shard_115.bin b/params_shard_115.bin new file mode 100644 index 0000000000000000000000000000000000000000..abeef90790275f05873e9d244458cfc9229c5db2 --- /dev/null +++ b/params_shard_115.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a9822ceb490c524674f19f48a3378f5d5f6b2a6b9e3a7699fa0c7f78dd69758 +size 25165824 diff --git a/params_shard_116.bin b/params_shard_116.bin new file mode 100644 index 0000000000000000000000000000000000000000..7f498ff4d664dfc4ad9c719f37bbbbc5c4694a00 --- /dev/null +++ b/params_shard_116.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9875e74a44ae9d182b66ebed25f0dd091e292714496de70537af3ddc5f02798 +size 50331648 diff --git a/params_shard_117.bin b/params_shard_117.bin new file mode 100644 index 0000000000000000000000000000000000000000..2b5ecfc2245f909bf2ff4af43215960e76df6ef7 --- /dev/null +++ b/params_shard_117.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:836ada6bb8988e7fb669d015bf5ee6759a46672ef739e753e801ce9df37826eb +size 24002560 diff --git a/params_shard_118.bin b/params_shard_118.bin new file mode 100644 index 0000000000000000000000000000000000000000..d082485ef43edd48715c62172215fa03c6b82b35 --- /dev/null +++ b/params_shard_118.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac525f4603e21d1f15651419b5e13db376bb3b9127b8284f9edb7761046d81b +size 25165824 diff --git a/params_shard_119.bin b/params_shard_119.bin new file mode 100644 index 0000000000000000000000000000000000000000..4fc3dd3c4b4d38863820ddb8b73a6dd47c5b3822 --- /dev/null +++ b/params_shard_119.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91644133dd61620c78735aa68893f97a909c932292f1b793050a654fc6464394 +size 50331648 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..c94c5f3bd0f8f47b00156e8c31a437480facee0c --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45809aa668fef8e1589882231d8d9c2ff7db3b8065ea412ea2b83f020c8327fc +size 25165824 diff --git a/params_shard_120.bin b/params_shard_120.bin new file mode 100644 index 0000000000000000000000000000000000000000..955b45d994a5f552e88cd0ffc7d8d136df9c7970 --- /dev/null +++ b/params_shard_120.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e22578bc032481672a7c008f0398b005d8c7d121ecd47ad46534497528d7355f +size 24002560 diff --git a/params_shard_121.bin b/params_shard_121.bin new file mode 100644 index 0000000000000000000000000000000000000000..533e8d6ac2b1b7b8d2219cdd0d3b531d680552e0 --- /dev/null +++ b/params_shard_121.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c3d6167f78f68826511b98ebeaddb515f553d400cbbcd40968abc48f2ea7d94 +size 25165824 diff --git a/params_shard_122.bin b/params_shard_122.bin new file mode 100644 index 0000000000000000000000000000000000000000..932d7106fd5b19d2f182169550b53f17b0d6b34f --- /dev/null +++ b/params_shard_122.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ca9a8574fae4db9b4a5bdbf342be46c32cb08c80b859b8e1a239b7a9fcc24d3 +size 50331648 diff --git a/params_shard_123.bin b/params_shard_123.bin new file mode 100644 index 0000000000000000000000000000000000000000..155d39db6ab0098a2e431f03061c1bc7fc33c540 --- /dev/null +++ b/params_shard_123.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9b3af6202857d6d758b5b7b90108b25b6568768857cfd68492fdd6f0cfd5f44 +size 24002560 diff --git a/params_shard_124.bin b/params_shard_124.bin new file mode 100644 index 0000000000000000000000000000000000000000..da8ea2e8f2073c5d08dc965cfa0019e39a04bc54 --- /dev/null +++ b/params_shard_124.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66327bfb42d75cd89b658e6bb914b459ca7b1b0e9a9cc2d4dc49117139962884 +size 25165824 diff --git a/params_shard_125.bin b/params_shard_125.bin new file mode 100644 index 0000000000000000000000000000000000000000..6bc05ee09991714820f09254a65aaac17efcdd65 --- /dev/null +++ b/params_shard_125.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e29706999b2d391b5b038730a7f3f9214612a186f2561e3984f73cc3476976 +size 50331648 diff --git a/params_shard_126.bin b/params_shard_126.bin new file mode 100644 index 0000000000000000000000000000000000000000..06fa677a5fcbdfac2cdb415990793f23c39db863 --- /dev/null +++ b/params_shard_126.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7355bf55513b3670ec12db50f4341f95e7e59a52bcf5e9875431325a4557ef95 +size 24002560 diff --git a/params_shard_127.bin b/params_shard_127.bin new file mode 100644 index 0000000000000000000000000000000000000000..b4f33181c9df9fe7710c84d516ba3d48399ee3df --- /dev/null +++ b/params_shard_127.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b87f6fb1f231947a7241b32f8a1eb1e9e9f4fd700dae1a9d8b93d38eb7f690b0 +size 21626880 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..bbf1d3eacd89835f4a53655bbf4612b5bfaac323 --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a86556076df4ae21cb607bf947c0741a15c41bf7536ef1c67f3fd377c8b49cce +size 50331648 diff --git a/params_shard_14.bin b/params_shard_14.bin new file mode 100644 index 0000000000000000000000000000000000000000..fbbf8962e6ab6df0aeb2e5afcd563406b98a5c8a --- /dev/null +++ b/params_shard_14.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fe52299f854c6edc523114f9670736053f4a603567f8ea666b77522edd42d4d +size 24002560 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..1c01c5301701ceb6aa01814a3e0441b6bac846a4 --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc5e21398f00790953acf895eab555ce69c97a2ca14275df727e8366293df09e +size 25165824 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..2bbad18aee40d36a6a20deb5ef6c1b4b72884f53 --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebaf7480f4983b9a2417cfeb3fd8eddab988cc4a2f622a11ed986e512d02fd75 +size 50331648 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d8280ac891757d0f08f6efab39a258fb6a0f77e --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91e431caae476d032d7248a584a647d7915a74b27989d87cf19d34cae382efdb +size 24002560 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..e7eadf6e19fade5338410ec8aef688361e299c18 --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c96e19a8f97fa785c056557262a0f0b38f5588cfa5b41a6c79c02a93897def97 +size 262144000 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..d818e22ffabd0cc0fe7cf37c5c74ce859c17fa6e --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b7618105ddd7e88164b899b86df5b4235872cb74be21bf02da97553dfa1c5e6 +size 25165824 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..c58e336df4b85ac42adaa5974ec2f5546e454c28 --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:371d0c2aae410fa984f0e9bed2d685fe0f291b55dfdcd4f5b6f440718f6c076e +size 50331648 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..be4cadce4e16867a839823807b7c803cc51b1c55 --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15cd93a14406cf844230a2181f32a04faadbe1ccda2f176044458017f54d9d7d +size 50331648 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..73c76248fe8e51008426c5f81e26b2593632094f --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67cf1c9c7811a3f458bf904678853e2c156c0d3aeba6fb41f959053a3465c117 +size 32202752 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d323bb0e661848b7a30b6c3a5a5e645648b1a60 --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15ed2ff038331b345da17741d640ea9b7e6aeddf735d254fc01fb5ecec1838e7 +size 25165824 diff --git a/params_shard_23.bin b/params_shard_23.bin new file mode 100644 index 0000000000000000000000000000000000000000..a12e492b223b2a299bad56835ffb18af8a5817a0 --- /dev/null +++ b/params_shard_23.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87227b01325039d39976544657d436e03d43c6436ac42f63ea3ae2405e55aa86 +size 50331648 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..addfcdcc72abeb788330eee3461a1e3595c2026e --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef47947c2a38d385c97960c994a828a3efe5395b0ee586c681f9a7e4a7260aa +size 24002560 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..e62af64a96554f56fdc8e1c15318d7d0e2f0fc81 --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2248dde5d57952c6d9bbaa0bed249e6624b68895b4c2a2681eb8aafd1aaa0a9e +size 21626880 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..a66a7b9b0621e6dd6b88cafd71af06f96e6a3fe9 --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e65475d245d452a154292520f2e8fda6d48e26aefd1d7144ba555668eb130358 +size 25165824 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..7fb98280520137bfdc5ecf2ce4a24067f47cae62 --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d195af9e7f8822b35c5ba34cff564af79173652e22afb10c620ad4dd9eac5735 +size 50331648 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..88a5bb6308377c8f793bb7786831b669bc5907a3 --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a68dcea62695019f0b1eaa7009003c5c8cc8911da240fe10a975f14cd58da168 +size 24002560 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..31f398eece114da1f57d69969561312bd4441d9f --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30fec9da08af31a78f25ac77950e877151cb21deea3e3b2d0cc58ce934969701 +size 25165824 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..ae89d1ad7b493dad84f74f136e6233cb0cf45631 --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed64ae0aed5114a25859dbe20129f162044e0adac620cf0b9e5468eb83c182fe +size 25165824 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..9a47803bb44429919217df8eb9e9755cd7ced56a --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:463762434363c0da23eba53fccab9be78f5e4ff1f9063b2182d8caa0dcef915e +size 50331648 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..043c3297a52237908651f099daa75c2041a16a39 --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81fbf0ccb1fa8d5f1406b49d73ba63d89123a2ed3c4166789479cb2642f79d87 +size 24002560 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc28527d1762b28924f3ac1af48a2a41757bb8d7 --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be4efd158b2a802b17d0d6f010d9edd739279ed9ca7c8aed2870ff52c1af7061 +size 25165824 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..623e5301885dffe701c3611c7172e6f52c213596 --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b82f2aab92a315da3a43ec4f36d588d1f8fb1ad6f4c34e76d97455bdc94b4115 +size 50331648 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..02b462de49b728df7159d656208ca0db8e8b90b1 --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ed5c4799b3c5c1e65a66e14036237971d42a092f8b1e7c86d97a6da6c4d9f6a +size 24002560 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..520116f233f02053fbfd5c0fb5946f98ee177bf8 --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3de96aa7ca6a1848aa0da71e7a16a108f3d89b332283d2912b4e44c8fee443d1 +size 25165824 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..9acf61c63151599496bff860b700fa76a2adf569 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e66c3620613413f9db800548014720ec3e1ee4003917b25f6371bd0823317b9a +size 50331648 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..ddb9e4f9f274c947d883f3456707ae6b28996422 --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d4bab7c38c4085ca4cb83aa6d843c6a3247a8adc3531f37166158f2223139f1 +size 24002560 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..f944fdfead5aaedfd17c8eb328a8a1e5ae3eb19d --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a48adff3bbb240893be0ae62fc3977bf4bbc7bad2b3ed1826a1e39c356826259 +size 25165824 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..b3aefa1db24dc6bd254524e7086acc88b2c34e6d --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62cbc76a042723ae274d3c16992572f6acfc139498cf43b402f074627d84b88b +size 50331648 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..81a8dcc88c6c619007e79217c0ce982ca299ff42 --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a64ae359eefd84a850ce32062f1f5ac73d45a63153290e5c823e05edb0da9820 +size 50331648 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..f2c09aaa6b184c3217ca0a380d45fbeb4ebf7a2a --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e4c69d41282b52ccbb939eea6839464a236da8a9d17a9bc00c8816d957ae511 +size 24002560 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..6d99f4202f31ddc7b6131b52db7902db97e5b09a --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016549095e7e96ab458d97603fb2bd9cc15a21cf9923872ef13c74307c8f5fe0 +size 25165824 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..af06d53e2ed65afa37400b1e02688ec95c3fc726 --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a3108220916a6ee06cb8f6ff84044691d3ba1fb2f87b43dfd2cf198a73a8ed6 +size 50331648 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..656f47a7eb053df0c12071f018a876d80b6ef8bc --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be2ad6d9d8f2069b6ac2ca7505c9c73181ccb0418548d90e569e05e76cd200fa +size 24002560 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a191cd8d65ceca33f9fc9c7a4ad9edc98d62102 --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40356bc0f843c8d3f1d50f9d6f3ee4f46523a8c1d4520faf0d9ab97b5eee6a1c +size 25165824 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..a95f59cf719b82068b944a63b7f6b884b38ab6ad --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3da48f248ac2b8b06609959c1208ded6e7e760300922decd22a7356fc40a35e3 +size 50331648 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..231987cd25d2070b7d823068973b67e534f49244 --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbbc2b1ec282895a31d0d9c01e22b5bc30d55a60e168c8598403b115c48e09f7 +size 24002560 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..89d1d76c28cf38a9a8f84fb2d4a3109ddaf6042d --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4680344ea0a6d47a29e2dba3f93e5e05d332ef45ab2b7828ab9a0af5af933fc +size 25165824 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..b9b69d749130cc2e47ed7fade69cb9005d30691f --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89240a374d105fa2fe4295d9f6aa8af33f547d4f9d176a860c00ea06ef630317 +size 50331648 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..ae5fa440a1c17b82beb9ee8a357b56e6d53eb72a --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca5c77d6eecf58b3c5b1bed594f8843aeaf8fbe476e5cb38da6fa4b809c7d338 +size 24002560 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..5dd033610ae0d17d2114ae1dd2a5acb4c53add4f --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcd02935b06568ced932046998060c0fbd69d0b0920f4c146309dc722fe40e45 +size 26370048 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..9e1efaabc087b92fac4612ea8f48da9b57aec4ee --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e217ef9015e2ace795d3adf76263ef9ad4d388c8c226039b16b335cd1e16e4c8 +size 25165824 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..1142586f82cf576cd75811b22b9d3bac5eb3da2d --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6549e9f922d23d14f84dbf1153cef9e619e957aaa0c86fcec234a4fc179ef987 +size 50331648 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..e9090ef2452bdafb8ec5633b8a5b6ba0e3385009 --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e261772bf49f3ecc7b372f7db0afbc74458310201099921e92db9e99e2a6a7c4 +size 25165824 diff --git a/params_shard_53.bin b/params_shard_53.bin new file mode 100644 index 0000000000000000000000000000000000000000..514d7c7abb0d0fcc6d33444b9c00f70b3fb940f0 --- /dev/null +++ b/params_shard_53.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12eabce6da8eb4d76b3b6f8ffdb71fa08b83e0073e8530686c3ef1f8daac304a +size 50331648 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..cff0a792f1087288703088c98b515d134bfadbd2 --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31822bb5eb0e3df7bd3e44a04ff2314c9de7fd4e9e84a202b49fc6d7f1b13225 +size 26378240 diff --git a/params_shard_55.bin b/params_shard_55.bin new file mode 100644 index 0000000000000000000000000000000000000000..ce9fe0c8e5dce856f7e98fdf8144877599bb0660 --- /dev/null +++ b/params_shard_55.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00e02b53a687541d9573bef2fc617c7bc7dd9b496092763a125ad2cdc25b4ed4 +size 25165824 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..e06ff61f2a217ac95268d3b15b956048d848a105 --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d0d6221ea747127c0ebfafef2be72a832d4fb47a1ca84aaca2784050b449018 +size 50331648 diff --git a/params_shard_57.bin b/params_shard_57.bin new file mode 100644 index 0000000000000000000000000000000000000000..d092643176346e69384a192cae453d044b261c2f --- /dev/null +++ b/params_shard_57.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1423dd09bc38fe56b0c25d069408d028e77b874d9d13d432ac879b20e4533dfb +size 24002560 diff --git a/params_shard_58.bin b/params_shard_58.bin new file mode 100644 index 0000000000000000000000000000000000000000..f745892728835dbbc6bed1657d0ba11016c4c608 --- /dev/null +++ b/params_shard_58.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:261cc8a43623cf2175fef10f7aa059aa001bf261f88ff54d202f042a2a4210df +size 25165824 diff --git a/params_shard_59.bin b/params_shard_59.bin new file mode 100644 index 0000000000000000000000000000000000000000..ecce27efcf9f62afe2630e76fb94333797991ef7 --- /dev/null +++ b/params_shard_59.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fde3b3776bd0cc86fa67064b8c7e09d9eaa1df9eb1326a62bcd73eac84fed0e0 +size 50331648 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..2da7045136683510a28ba38008787e049a1250de --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44307e3bf01173ae47bc92735da0aced04bfe87e5b963bc1334f4477a7e6d211 +size 25165824 diff --git a/params_shard_60.bin b/params_shard_60.bin new file mode 100644 index 0000000000000000000000000000000000000000..f881ad7ab1f271175727611585d6a74d493524b4 --- /dev/null +++ b/params_shard_60.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b7c1b1759c804c6bf0b20304a9a1b4f6b61f98417076bfd1b81dd1d3ce370ba +size 24002560 diff --git a/params_shard_61.bin b/params_shard_61.bin new file mode 100644 index 0000000000000000000000000000000000000000..9e1ab536825d36360b3d4a4c4612e3b20f7ba3f2 --- /dev/null +++ b/params_shard_61.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:801f7dc2cfa1602043a7d0e701e5b253f3c2caca32915b193d38aeffa5143ca0 +size 25165824 diff --git a/params_shard_62.bin b/params_shard_62.bin new file mode 100644 index 0000000000000000000000000000000000000000..4c7321984c60b44a875320fb2451a14d4b78008d --- /dev/null +++ b/params_shard_62.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3223cb41e3e8961c45509eb8d35e175322391724d5828d3f2245a7b209cb872 +size 50331648 diff --git a/params_shard_63.bin b/params_shard_63.bin new file mode 100644 index 0000000000000000000000000000000000000000..df26153182a3ac5b050602e8d1983200b5598768 --- /dev/null +++ b/params_shard_63.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6da11e2ba83334d55d7e4bdc1e7f40b111b50b5abf4905be235d2efbf554e3d4 +size 24002560 diff --git a/params_shard_64.bin b/params_shard_64.bin new file mode 100644 index 0000000000000000000000000000000000000000..4be3c963585313a825a48ae068a5beffaf407185 --- /dev/null +++ b/params_shard_64.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c50ed53e7188ddc3b75978c92cbcba2c93a8b9e2dc269e203980989634850267 +size 25165824 diff --git a/params_shard_65.bin b/params_shard_65.bin new file mode 100644 index 0000000000000000000000000000000000000000..ae47b66504e1b7dca0fd3891fa55dfb7534f0a3f --- /dev/null +++ b/params_shard_65.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e574301fd147ff019cf8bc7842f3497d8e72e82c120f7d6c8b418dd4c5f8bb +size 50331648 diff --git a/params_shard_66.bin b/params_shard_66.bin new file mode 100644 index 0000000000000000000000000000000000000000..f3450ef29b93405a344cc5d88f0c603ca6801e37 --- /dev/null +++ b/params_shard_66.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1b2c3bb0297bb0c847948d65a53b86a603c8e439df228b6f2e2cb6b49cf56ec +size 24002560 diff --git a/params_shard_67.bin b/params_shard_67.bin new file mode 100644 index 0000000000000000000000000000000000000000..359c4bcb599edc03935b7216ebdb4ea1d278cadd --- /dev/null +++ b/params_shard_67.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:387cc295bad68a7e17e111f9e3174a24cb10191aa01fb779ba74185c8954e5ad +size 25165824 diff --git a/params_shard_68.bin b/params_shard_68.bin new file mode 100644 index 0000000000000000000000000000000000000000..56ef0aa1a13b8c9638572a8e7e66f97140643def --- /dev/null +++ b/params_shard_68.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d04d34f93d26d263f9e3e955bc0113601613a39a6c1bd99a043c93185c95c05 +size 50331648 diff --git a/params_shard_69.bin b/params_shard_69.bin new file mode 100644 index 0000000000000000000000000000000000000000..87fae8b02b51ca0283e85cf37ace78dd2edd9868 --- /dev/null +++ b/params_shard_69.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25124f2bdaebf5ff5faafa06dddbd3962da3e80eec7b7c09b7e43625de6216a6 +size 24002560 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..792042914cbb7b2172b10fc66a0ced6ee22ba26b --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:900081f6eb166b0b333975273acaea89b4ea38ef97d0ade74ec8fdce4e75e8f0 +size 50331648 diff --git a/params_shard_70.bin b/params_shard_70.bin new file mode 100644 index 0000000000000000000000000000000000000000..7f23c6e11a33348dbd6f5e6ed9163302ed14ae0c --- /dev/null +++ b/params_shard_70.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:850c2179b10a95be273ae37ddfc17c344a8248d81c821a25b8127a4185426477 +size 25165824 diff --git a/params_shard_71.bin b/params_shard_71.bin new file mode 100644 index 0000000000000000000000000000000000000000..d3b451f28b81bbdb8816995bc2fc6c12cba9abd0 --- /dev/null +++ b/params_shard_71.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c508b8467fd648a951a1e6635a0fc00e87acf93b5f977e1007e18f0a62bd5ad +size 50331648 diff --git a/params_shard_72.bin b/params_shard_72.bin new file mode 100644 index 0000000000000000000000000000000000000000..65f97cf8a4790c72b03d479a8cc6391842e7c42a --- /dev/null +++ b/params_shard_72.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7561becd909ad0b4589d06b12a5918b09f6eb0fbdaeb6f591eac88949f14e83 +size 24002560 diff --git a/params_shard_73.bin b/params_shard_73.bin new file mode 100644 index 0000000000000000000000000000000000000000..6ede34e3f5e482c1ba0624307972a03ad4c704a7 --- /dev/null +++ b/params_shard_73.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e167fac55be0d529915676659bf6dc09c9fb978ac80bea62655145dcc67dfe89 +size 25165824 diff --git a/params_shard_74.bin b/params_shard_74.bin new file mode 100644 index 0000000000000000000000000000000000000000..f09f6cfae0e6d38b67dc7e00e3a43140af61c23a --- /dev/null +++ b/params_shard_74.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5a274b9484704e38d243018e1e1ba43993023cf32dcaec15aba9a0fc7552e9e +size 50331648 diff --git a/params_shard_75.bin b/params_shard_75.bin new file mode 100644 index 0000000000000000000000000000000000000000..d6dff307ed6d145977c972c886e8d3368206a025 --- /dev/null +++ b/params_shard_75.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a2f71142ba9715fa3e767a3cac4e503644d361166bb4617657f13d32a436fe +size 24002560 diff --git a/params_shard_76.bin b/params_shard_76.bin new file mode 100644 index 0000000000000000000000000000000000000000..e08b15d5dbbbada8d13b0ab7a51691be77bd1a1a --- /dev/null +++ b/params_shard_76.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7de6dc3cb30c134809922e1081a1f81864acab1a85a2c81341c31b173c56cc6 +size 25165824 diff --git a/params_shard_77.bin b/params_shard_77.bin new file mode 100644 index 0000000000000000000000000000000000000000..e84d185b2ff3e1fbf7579ae1ae0e6e92bf353faa --- /dev/null +++ b/params_shard_77.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edac29fa0fa9739d540a1249508e6e9a1f8f94510635dd13ea711f9575a009c8 +size 50331648 diff --git a/params_shard_78.bin b/params_shard_78.bin new file mode 100644 index 0000000000000000000000000000000000000000..f04c3d493141e63ada8dc907eac997f36c71d067 --- /dev/null +++ b/params_shard_78.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56172fcf16093507a29089dc37247f78a7f54b4ccb3d20dbb6a9a8740c683188 +size 24002560 diff --git a/params_shard_79.bin b/params_shard_79.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc9c85e7783cc1af5ad76dd0b000b7aba78b7560 --- /dev/null +++ b/params_shard_79.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db0fb7783ae776aadbcc5ec140eb7a6bbe986e064d8d4322312c64f3498e5ef1 +size 25165824 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..a55a6217a64ba82e35ad19fd8f20be1502e76a6e --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ee94a5275e14cfc32622fd5944fc4d876ecf3a3278c765ff52ef8317428bdcc +size 24002560 diff --git a/params_shard_80.bin b/params_shard_80.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c1584964ee97dd4ebd048ea751411751767b7d5 --- /dev/null +++ b/params_shard_80.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09fdb7c93094ca67534d250c5ac1fb9654d3ec6ff3947b91d4252699a6fffa04 +size 50331648 diff --git a/params_shard_81.bin b/params_shard_81.bin new file mode 100644 index 0000000000000000000000000000000000000000..abe304a881ffc8f03d07cb288758192e60fc2db7 --- /dev/null +++ b/params_shard_81.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41d173320161c63984064a2184148b30dabd194731c03993668e032b83553956 +size 24002560 diff --git a/params_shard_82.bin b/params_shard_82.bin new file mode 100644 index 0000000000000000000000000000000000000000..313b460f18b153d78b0d95c5eccfa6f8807c25ab --- /dev/null +++ b/params_shard_82.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fd59c61413527675f2a68ea9f24c1c5e3b3b142bb15df2bc7e3c32c976b349b +size 25165824 diff --git a/params_shard_83.bin b/params_shard_83.bin new file mode 100644 index 0000000000000000000000000000000000000000..1a3698b55a206ceaf81dde9ab118749b5e16f813 --- /dev/null +++ b/params_shard_83.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7090c31ad1784886ac06883121c563dacad9bdc8eaaf8ba531ec5d5fa77ac8fc +size 50331648 diff --git a/params_shard_84.bin b/params_shard_84.bin new file mode 100644 index 0000000000000000000000000000000000000000..6480017b1067261f4b5bc9ca4f7ecf147b97ad8a --- /dev/null +++ b/params_shard_84.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea34e311e539bd4d3f82ff904d02a56d688ffce8670b8e86d4612c6dcb041b1 +size 24002560 diff --git a/params_shard_85.bin b/params_shard_85.bin new file mode 100644 index 0000000000000000000000000000000000000000..97a7b8de9668ca8d1dbd13cf4ce3fb8bbdf1f43f --- /dev/null +++ b/params_shard_85.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:500049fcd64153a9dae60b26486cd95be5c6c0baac2a364295329e6d3b902e19 +size 25165824 diff --git a/params_shard_86.bin b/params_shard_86.bin new file mode 100644 index 0000000000000000000000000000000000000000..dc6ced820667311f82aabce6912d4b6c5476d65d --- /dev/null +++ b/params_shard_86.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d993a05cf1e46574dc8b56a69622b7d9867037c5980082a07ffc2767e1a3843c +size 50331648 diff --git a/params_shard_87.bin b/params_shard_87.bin new file mode 100644 index 0000000000000000000000000000000000000000..f40e53fe44e1af897981e9bc644f597e2c9f3a85 --- /dev/null +++ b/params_shard_87.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7677aaaece7edeb446255c9e728aec1f76c3fc2418972532358074fdba84b9e +size 24002560 diff --git a/params_shard_88.bin b/params_shard_88.bin new file mode 100644 index 0000000000000000000000000000000000000000..51480c59eaa05211b688ca4b38d9ec2bbebc42d0 --- /dev/null +++ b/params_shard_88.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b27d5119873d1c85056d1c439b90027c50955df96371a354860ac28d6e0d2f9 +size 21626880 diff --git a/params_shard_89.bin b/params_shard_89.bin new file mode 100644 index 0000000000000000000000000000000000000000..543923fc44b7aadfd38174820ab0eb51c5581d0f --- /dev/null +++ b/params_shard_89.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cd54d84b96dfe1f38905b02cc2f9e1ea6981cc690d22bb39f9324d68f1f3720 +size 25165824 diff --git a/params_shard_9.bin b/params_shard_9.bin new file mode 100644 index 0000000000000000000000000000000000000000..4a55e5b1a051baa3a9b386ba963c8a3382e0d028 --- /dev/null +++ b/params_shard_9.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55948ac1ae7b00f6ad58f063ef5901458d02c19d77a8a9389038907b4ef4c53b +size 25165824 diff --git a/params_shard_90.bin b/params_shard_90.bin new file mode 100644 index 0000000000000000000000000000000000000000..5aadc252216148bf05e2a9de9f1e75ce73ec9c39 --- /dev/null +++ b/params_shard_90.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c00707f6b3894947093522b5d899dad6e7e676f4cf412cd1139fd1cece97a933 +size 50331648 diff --git a/params_shard_91.bin b/params_shard_91.bin new file mode 100644 index 0000000000000000000000000000000000000000..0a3f20bca5b424ee0e02968af889b9bba473252d --- /dev/null +++ b/params_shard_91.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fb64ae2d725c2d3c7d0464ec5fee64210afdbc5de50b8994ea8fe9d0cc3878e +size 25165824 diff --git a/params_shard_92.bin b/params_shard_92.bin new file mode 100644 index 0000000000000000000000000000000000000000..595b8ae36d8168021a55f9a2bb6dd23ad1a91963 --- /dev/null +++ b/params_shard_92.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003238576022f0f9b4b3fa4192516bde7378e0724ce1c1cc0c66dde2c5ada0c5 +size 50331648 diff --git a/params_shard_93.bin b/params_shard_93.bin new file mode 100644 index 0000000000000000000000000000000000000000..2a3cfc71fc3decfc7c2be1c9742582249edefd8e --- /dev/null +++ b/params_shard_93.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa5d1fe58301a3855cd1e4e67059508d073aa9cad67f92377059bda3e74d2e7d +size 26378240 diff --git a/params_shard_94.bin b/params_shard_94.bin new file mode 100644 index 0000000000000000000000000000000000000000..96d756b643ea2135a1312ebdd65897dd379371e0 --- /dev/null +++ b/params_shard_94.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53be8e58afa52e522d37b7faa13336156394d77f2150719e854be1f0110da4fd +size 25165824 diff --git a/params_shard_95.bin b/params_shard_95.bin new file mode 100644 index 0000000000000000000000000000000000000000..614f12577511a5da54a40d8585edd82ed16d463a --- /dev/null +++ b/params_shard_95.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eb98629b689535f3b5047dc3847bddd198b2a2627b2d62ad1a7158aa6f01d58 +size 50331648 diff --git a/params_shard_96.bin b/params_shard_96.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ecbf05ced1b307c0ec5058aa60c3cc90b2aca2d --- /dev/null +++ b/params_shard_96.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ab0d8a711dcebcd1fab6b460dc79fec5b8174838f85dc21379b97fdf7dedc2b +size 24002560 diff --git a/params_shard_97.bin b/params_shard_97.bin new file mode 100644 index 0000000000000000000000000000000000000000..8bce400c5e8dbf126fa800c061b4f39418893dc8 --- /dev/null +++ b/params_shard_97.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b941dac78896953086bd61ce36ae14da22ce042a4de41e5051c95823e07bccc8 +size 25165824 diff --git a/params_shard_98.bin b/params_shard_98.bin new file mode 100644 index 0000000000000000000000000000000000000000..518b2dc815ea8c3f9161ced985dfb99345eac3e5 --- /dev/null +++ b/params_shard_98.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbb5417070ef47c133b65bfc801327e9e6901aeb92b239b37a5ffc0e2986ff58 +size 50331648 diff --git a/params_shard_99.bin b/params_shard_99.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1a3afed540772047bc89e5ee5840b876c022e53 --- /dev/null +++ b/params_shard_99.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe870e8bca3fea56e4a1f1c29a4b871760a122a4458112186827498bdc105bff +size 24002560 diff --git a/private-llm-config.json b/private-llm-config.json new file mode 100644 index 0000000000000000000000000000000000000000..f6b20f10d5331b2ba0152385c46e23b11a81be75 --- /dev/null +++ b/private-llm-config.json @@ -0,0 +1,46 @@ +{ + "model_type": "llama", + "quantization": "GPTQ-Int4", + "model_config": { + "hidden_size": 4096, + "intermediate_size": 12288, + "num_attention_heads": 32, + "num_hidden_layers": 42, + "rms_norm_eps": 1e-05, + "vocab_size": 128000, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "rope_scaling": null, + "context_window_size": 4096, + "prefill_chunk_size": 128, + "num_key_value_heads": 8, + "head_dim": 128, + "tensor_parallel_shards": 1, + "pipeline_parallel_stages": 1, + "max_batch_size": 80 + }, + "vocab_size": 128000, + "context_window_size": 4096, + "sliding_window_size": -1, + "prefill_chunk_size": 128, + "attention_sink_size": -1, + "tensor_parallel_shards": 1, + "mean_gen_len": 128, + "max_gen_len": 512, + "shift_fill_factor": 0.3, + "temperature": 0.7, + "presence_penalty": 0.2, + "frequency_penalty": 0.2, + "repetition_penalty": 1.2, + "top_p": 0.98, + "conv_template": "eurollm", + "pad_token_id": 0, + "bos_token_id": 3, + "eos_token_id": 4, + "tokenizer_files": [ + "tokenizer.model", + "tokenizer.json", + "tokenizer_config.json" + ], + "version": "0.1.0" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..4eda61927ffb932c5325cea423ee63de804933ee --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:923e2c68bc44c2886322dadc77c3ad14b7f803d5dace5917c3aa5d321a4202b4 +size 8224136 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..062965b46a632a45edeabf89743723750bd57f75 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42957aec88804838805b335da1bbcce9d116024a20c6c4b56757648b9e348254 +size 2408875 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..219a276cd5b47a202af8eb118ee341946bac1c63 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2108 @@ +{ + "add_bos_token": false, + "add_eos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "5": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "108": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "217": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "218": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "219": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "220": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "221": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "222": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "223": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "224": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "225": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "226": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "227": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "228": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "229": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "230": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "231": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "232": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "233": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "234": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "235": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "236": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "237": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "238": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "239": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "240": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "241": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "242": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "243": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "244": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "245": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "246": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "247": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "248": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "249": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "250": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "251": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "252": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "253": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "254": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "256": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "257": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "258": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "259": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "260": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "", + "chat_template": "{% for message in messages %}{% if message['role'] == 'assistant' %}{% set role = 'assistant' %}{% else %}{% set role = message['role'] %}{% endif %}<|im_start|>{{ role }}\n{{ message['content'] | trim }}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": true +}