Add files from e3

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "/fast/rolmedo/models/falcon-11b/snapshots/model/",
+  "activation": "gelu",
+  "alibi": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-11B--configuration_falcon.FalconConfig",
+    "AutoModel": "tiiuae/falcon-11B--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-11B--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-11B--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "ff_factor": 4,
+  "ffn_hidden_size": 16384,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 8192,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": true,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 60,
+  "num_kv_heads": 8,
+  "num_ln_in_parallel_attn": 1,
+  "parallel_attn": true,
+  "rope_scaling": null,
+  "rope_theta": 500042.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "transformers_version": "4.41.1"
+}

pytorch_model-00001-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e020673bb54c0cb31872c36f19466dc37c35637d93c8557155d09b87c792277
+size 4978861838

pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d525272e48ac2588620f70d050226140b88c3949c32102a35d7718f3bb861f75
+size 4932760078

pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e833e5c24031947358e1f0fbad61c10059655397e3c6e6d7bbb262c5941d2731
+size 4932760078

pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac4a34f648765f6561e634071cb609c479392b4f669a0ac3c02a7420117be89
+size 4932760078

pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0781cd240e6218006acdb88cf5d63066b75155f509c9f2825a24e9ca404b5b4a
+size 2428629234

pytorch_model.bin.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_size": 22205644800
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00005.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.30.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.30.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.30.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.31.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.31.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.31.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.32.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.32.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.32.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.32.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.32.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.32.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.33.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.33.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.33.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.33.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.33.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.33.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.34.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.34.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.34.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.34.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.34.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.34.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.35.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.35.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.35.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.35.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.35.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.35.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.36.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.36.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.36.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.36.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.36.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.36.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.37.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.37.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.37.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.37.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.37.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.37.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.38.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.38.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.38.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.38.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.38.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.38.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.39.input_layernorm.bias": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.39.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.39.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.39.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.39.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.39.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.40.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.40.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.40.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.40.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.40.self_attention.dense.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.40.self_attention.query_key_value.weight": "pytorch_model-00003-of-00005.bin",
+    "transformer.h.41.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.41.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.41.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.41.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.41.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.41.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.42.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.42.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.42.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.42.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.42.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.42.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.43.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.43.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.43.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.43.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.43.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.43.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.44.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.44.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.44.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.44.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.44.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.44.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.45.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.45.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.45.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.45.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.45.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.45.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.46.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.46.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.46.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.46.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.46.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.46.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.47.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.47.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.47.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.47.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.47.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.47.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.48.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.48.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.48.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.48.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.48.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.48.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.49.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.49.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.49.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.49.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.49.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.49.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.50.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.50.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.50.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.50.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.50.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.50.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.51.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.51.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.51.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.51.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.51.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.51.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.52.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.52.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.52.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.52.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.52.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.52.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.53.input_layernorm.bias": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.53.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.53.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.53.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.53.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.53.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.54.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.54.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.54.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.54.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.54.self_attention.dense.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.54.self_attention.query_key_value.weight": "pytorch_model-00004-of-00005.bin",
+    "transformer.h.55.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.55.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.55.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.55.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.55.self_attention.dense.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.55.self_attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.56.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.56.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.56.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.56.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.56.self_attention.dense.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.56.self_attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.57.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.57.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.57.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.57.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.57.self_attention.dense.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.57.self_attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.58.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.58.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.58.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.58.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.58.self_attention.dense.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.58.self_attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.59.input_layernorm.bias": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.59.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.59.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.59.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.59.self_attention.dense.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.59.self_attention.query_key_value.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00005.bin",
+    "transformer.ln_f.bias": "pytorch_model-00005-of-00005.bin",
+    "transformer.ln_f.weight": "pytorch_model-00005-of-00005.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00005.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "bos_token": {
+    "content": ">>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,135 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "500": {
+      "content": ">>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "bos_token": ">>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'User: \n' + message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ 'System: ' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ 'Falcon:\n'  + message['content']}}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Falcon:' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "device_map": "cuda:2",
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}