Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 6,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,24 @@
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+gate_mode: approach # one of "hidden", "cheap_embed", or "random"
+dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
+## (optional)
+# experts_per_token: 2
+experts:
+  - source_model: Treza12/Biomistral-Class0-Full
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Screening"
+  - source_model: Treza12/Biomistral-Class1-Full
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Diagnosis"
+  - source_model: Treza12/Biomistral-Class2-Full
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Staging"
+  - source_model: Treza12/Biomistral-Class3-Full
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Treatment Selection"
+  - source_model: Treza12/Biomistral-Class4-Full
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Prognosis" 
+  - source_model: Treza12/Biomistral-Class5-Full
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Follow-up" 

model-00001-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc87a3545b359e53375e28589c2d91225e4c8a2686207dc648721bc9b8991cc
+size 991971528

model-00002-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562dc7b4932c29db0fe00b020466e513c2aa1dbff21f0a8b48b9dab7e657a983
+size 964708960

model-00003-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e26f7480ea0b91132b9c2a42302a37a292133576a4fa86f429b9d1fdb78a312
+size 964708960

model-00004-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d86c7f7229cb0138695d05e831a48ae38e2b0ae2279386872040b0bbecf41e46
+size 964708960

model-00005-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cdd9f4b382f1d23be22296b7c4999cfc6d0bf9e98fb84590e0a7b185108c086
+size 989866488

model-00006-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9cd8c7f1952fd70360fe43b33a52613337ad6f67c162e548547e9486e8c9b71
+size 973089048

model-00007-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba7578bd6406ef2da0224a593e88cee4745f381983f39b526c46f3ff81494b2d
+size 964708960

model-00008-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a0d2ea84ca07bc916f08226035e7ffc22c4fcdacb30b671549c5a3f06eb6af
+size 964708960

model-00009-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44394221b07741a98465c41e061788b5656e703c9f8bd60b72ef569597ec254
+size 964708960

model-00010-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21262a3cf0cf453ca18ce5cc8164256daebaf21f5d85d8d8684ef762cb0ada43
+size 964708960

model-00011-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81018fa4d246ff1c094bf2b31dfb00faff155c9547328b69b29d1a645eea9020
+size 964708960

model-00012-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a945fae367cc6ec84dd7b83eda9d1efb02e3a4a855546b9d0d16b208628334b
+size 998254872

model-00013-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932771d7a67c049ce993e558734fc4940ac6f75a94f5cd29c3364d205f123540
+size 964700680

model-00014-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6114bc3e3efa049e8f66ce874a38f1eb3177f90311d72a739bf660706e39a6
+size 964708984

model-00015-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22278c0a9c5af288c7043b08cdc335416e0a4b65d4e27b05988ae3c20f8f06f0
+size 964708984

model-00016-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b98fd57907004b6acdaa50c0abf300fe2075cb80c3e4af0b631645af95ba2d5
+size 964708984

model-00017-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3304a2634a855d01762564b2e89dbdc30bc7bbae0d52d80c470da36fd7841b98
+size 964708984

model-00018-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e57701162a4db68ac1ede9a736837637be19a16f98bf5bb2795a1e86b14926d2
+size 964708984

model-00019-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9704cc0ac983b43585ebe232ee0086f693001b51c175ece7a9a1c1f5b61a7f48
+size 998246592

model-00020-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc9b10a36990975e29768d81ce0c85e5c969490f23424e1a69aff7fe04fa63c
+size 964708984

model-00021-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac59102eeaab958cbefa3619b635151827c8bd328a31ace89cd4c2fc42d7394
+size 964708984

model-00022-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ebc07461c701e3292ab896616f45f13ac0b2c38505a035b8c092d3ce5ef91bf
+size 964708984

model-00023-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2e0fa86fade3efddcfec53a31b1c10409d5567cc74f990ee6b8e0688c32edc
+size 964708984

model-00024-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b82835a1987d356529230c0c7e8d32cabfb8813b8ccc20efe8471096176f97
+size 964708984

model-00025-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d333a0ecdc03710dc951b518ada3de54d347e24ea53edc6a430f79057c5fc7
+size 989866504

model-00026-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aed2feb14172aba53af671183662ad4d508e4a32e922a6a670485b7c536dc44
+size 973089072

model-00027-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84dbed22dd0c6c0f7d6a4bde3a7ac72a24de02bd00758c592f57a97716a4d842
+size 964708984

model-00028-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d7e0c13262dd4081d7221d28b908ee64b939bb35104363684b88cd8db9cbf61
+size 964708984

model-00029-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c61feb4589f40fcf5371135e1e322f95d420f30c1351b1655dfbb1e508fede2
+size 964708984

model-00030-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d819e510960d087e26e4c35e3fc19d7f722a667e85d915dc53e970abffa31683
+size 964708984

model-00031-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ae2036e06eff9cc905a56d19286bbdba47a8bf6ffc868bfa65cadf8861b9bbc
+size 964708984

model-00032-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690a6646c30c04e82627fea71c2f05f8abb432e5850ff5265a80010b85f7e1f7
+size 998254896

model-00033-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64dd76d469b5af8396a3f9cd86cb636968f3c7c8917b28ff7309db1ce758018
+size 964700680

model-00034-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6737f33f672e86071ec851f433516b4efa96db08ec558d6368a2b08d07060f2e
+size 964708984

model-00035-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a01d917c279a130504aed7e92d613149a14d1559fb6e2947783f24ebbf1c32
+size 964708984

model-00036-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b0002a7519ad5d1fe39e056584604072498f4a0dc759f5272d5ed2cd7908e1
+size 964708984

model-00037-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb32f7ad24e2344a3546811260873e5300cbef2b541cc7f7c7872e5e7de8f332
+size 964708984

model-00038-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ef5d994ac6f1512d8385aea1ed457c470ae575f86daa6e2504e46d775a6eaf
+size 880814104

model-00039-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:045f6844fc217fbc321808e765f39a8edc594e08390423dfb47c933ed0a5a4e2
+size 263720760

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 37033615360}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00039.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00039.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00039.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00039.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00039.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00039.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00039.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00039.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00039.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00039.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00039.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00039.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00039.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00039.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00039.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00039.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00039.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00039.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00039.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00039.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00039.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00039.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00039.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00039.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00039.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00039.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00039.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00039.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00039.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00039.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00039.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00039.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00039.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00039.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00039.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00039.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00039.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00039.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00039.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00039.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00039.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00039.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00039.safetensors", "model.layers.6.input_layernorm.weight": "model-00008-of-00039.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00039.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00039.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00039.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00039.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00039.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00039.safetensors", "model.layers.7.input_layernorm.weight": "model-00009-of-00039.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00039.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00039.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00039.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00039.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00039.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00039.safetensors", "model.layers.8.input_layernorm.weight": "model-00010-of-00039.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00039.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00039.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00039.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00039.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00039.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00039.safetensors", "model.layers.9.input_layernorm.weight": "model-00011-of-00039.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00039.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00011-of-00039.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00039.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00039.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00039.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00039.safetensors", "model.layers.10.input_layernorm.weight": "model-00012-of-00039.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00013-of-00039.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00013-of-00039.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00013-of-00039.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00013-of-00039.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00039.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00039.safetensors", "model.layers.11.input_layernorm.weight": "model-00014-of-00039.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00014-of-00039.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00014-of-00039.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00014-of-00039.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00014-of-00039.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00039.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00039.safetensors", "model.layers.12.input_layernorm.weight": "model-00015-of-00039.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00015-of-00039.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00015-of-00039.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00015-of-00039.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00015-of-00039.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00039.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00039.safetensors", "model.layers.13.input_layernorm.weight": "model-00016-of-00039.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00016-of-00039.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00016-of-00039.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00016-of-00039.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00016-of-00039.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00039.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00039.safetensors", "model.layers.14.input_layernorm.weight": "model-00017-of-00039.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00017-of-00039.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00017-of-00039.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00017-of-00039.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00017-of-00039.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00017-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00039.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00039.safetensors", "model.layers.15.input_layernorm.weight": "model-00018-of-00039.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00018-of-00039.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00018-of-00039.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00018-of-00039.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00018-of-00039.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00018-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00039.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00020-of-00039.safetensors", "model.layers.16.input_layernorm.weight": "model-00020-of-00039.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00020-of-00039.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00020-of-00039.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00020-of-00039.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00020-of-00039.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00021-of-00039.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00021-of-00039.safetensors", "model.layers.17.input_layernorm.weight": "model-00021-of-00039.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00021-of-00039.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00021-of-00039.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00021-of-00039.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00021-of-00039.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00021-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00022-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00022-of-00039.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00022-of-00039.safetensors", "model.layers.18.input_layernorm.weight": "model-00022-of-00039.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00022-of-00039.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00022-of-00039.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00022-of-00039.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00022-of-00039.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00023-of-00039.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00039.safetensors", "model.layers.19.input_layernorm.weight": "model-00023-of-00039.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00023-of-00039.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00023-of-00039.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00023-of-00039.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00023-of-00039.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00023-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00023-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00024-of-00039.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00024-of-00039.safetensors", "model.layers.20.input_layernorm.weight": "model-00024-of-00039.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00024-of-00039.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00024-of-00039.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00024-of-00039.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00024-of-00039.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00024-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00025-of-00039.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00025-of-00039.safetensors", "model.layers.21.input_layernorm.weight": "model-00025-of-00039.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00025-of-00039.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00025-of-00039.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00025-of-00039.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00026-of-00039.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00027-of-00039.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00027-of-00039.safetensors", "model.layers.22.input_layernorm.weight": "model-00027-of-00039.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00027-of-00039.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00027-of-00039.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00027-of-00039.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00027-of-00039.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00028-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00028-of-00039.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00028-of-00039.safetensors", "model.layers.23.input_layernorm.weight": "model-00028-of-00039.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00028-of-00039.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00028-of-00039.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00028-of-00039.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00028-of-00039.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00028-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00029-of-00039.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00029-of-00039.safetensors", "model.layers.24.input_layernorm.weight": "model-00029-of-00039.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00029-of-00039.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00029-of-00039.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00029-of-00039.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00029-of-00039.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00030-of-00039.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00030-of-00039.safetensors", "model.layers.25.input_layernorm.weight": "model-00030-of-00039.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00030-of-00039.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00030-of-00039.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00030-of-00039.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00030-of-00039.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00030-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00030-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00030-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00031-of-00039.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00039.safetensors", "model.layers.26.input_layernorm.weight": "model-00031-of-00039.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00031-of-00039.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00031-of-00039.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00031-of-00039.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00031-of-00039.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00031-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00032-of-00039.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00032-of-00039.safetensors", "model.layers.27.input_layernorm.weight": "model-00032-of-00039.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00033-of-00039.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00033-of-00039.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00033-of-00039.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00033-of-00039.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00033-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00034-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00034-of-00039.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00034-of-00039.safetensors", "model.layers.28.input_layernorm.weight": "model-00034-of-00039.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00034-of-00039.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00034-of-00039.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00034-of-00039.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00034-of-00039.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00034-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00035-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00035-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00035-of-00039.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00035-of-00039.safetensors", "model.layers.29.input_layernorm.weight": "model-00035-of-00039.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00035-of-00039.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00035-of-00039.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00035-of-00039.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00035-of-00039.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00036-of-00039.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00036-of-00039.safetensors", "model.layers.30.input_layernorm.weight": "model-00036-of-00039.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00036-of-00039.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00036-of-00039.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00036-of-00039.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00036-of-00039.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00036-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00037-of-00039.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00037-of-00039.safetensors", "model.layers.31.input_layernorm.weight": "model-00037-of-00039.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00037-of-00039.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00037-of-00039.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00037-of-00039.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00037-of-00039.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00037-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00037-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00038-of-00039.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00038-of-00039.safetensors", "model.norm.weight": "model-00038-of-00039.safetensors", "lm_head.weight": "model-00039-of-00039.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00039-of-00039.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.first and system_message is defined %}\n            {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n        {%- else %}\n            {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ' + message['content'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}