Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BioMistral/BioMistral-7B",
+  "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": 3,
+  "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": "4.45.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,15 @@
+base_model: BioMistral/BioMistral-7B
+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-Unsloth-Full-Class-0
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Screening"
+  - source_model: Treza12/BioMistral-Unsloth-Full-Class-1
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Diagnosis"
+  - source_model: Treza12/BioMistral-Unsloth-Full-Class-2
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Staging"

model-00001-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e6bf3bfb0f7bc21764f5350a90fb4f894221a460db664bef1740e0a7320113
+size 933250496

model-00002-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c3174cc13770553da170452c91b5339bd11f10397e6c124c84e2adc2bfee094
+size 905987672

model-00003-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13a849044f3faefcbfd1e90f93f653e503289d8111d8d0dcf62e8cc05706a5d
+size 905987672

model-00004-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59fb5d56b7101a165ea10e16e8c892f882d03a59d2a1caf4e343cc95b92f307
+size 989865456

model-00005-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:115224a4953f9399237ec7b2546e459660b6b522c66addd194e57742bcad7d9a
+size 973088024

model-00006-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8585fff5dc9589e1a45ece7b0e86d7897d26b65512d2c489da03dbe52187d7ed
+size 905987672

model-00007-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac13a6eacda41b41c5c83065a62bc1624131d1dfe3ea7a43321e7a3542c2cd89
+size 905987672

model-00008-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d34dcd42533eb7301b531ae654d370f582e096bc40206a173d3e977d8c2fb98
+size 905987672

model-00009-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9664833733fb3db3c8aef7afd02fe29cae1fa7df9d08685b120f55480486cd1
+size 905987672

model-00010-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c7fdf803d0f62524fab6654012bbbcba65c128abca50fcd76ab9ed4096028a
+size 939525160

model-00011-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6ec907f11cdaefacae92af010d6de55ceff68410a0d3cd87b513d553a41def
+size 905987672

model-00012-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93d1e81b0fc0c149ec69350d609f72bc3aa4abaecfb60a6169d99cb9fb7bb0a
+size 905987672

model-00013-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0c21ca3726c5b9fa170d8eb48a70807a7a4cf5d301cc740832417ac2e0a27b
+size 905987680

model-00014-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71ed6d5f362d99cfc72238a36bf6b5b5b5e06d008064ba80a98bf9008fb26349
+size 905987688

model-00015-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b45c27bbebfbc74b93dfec24e891a3bb5363243c7f18e3c0e1fe624ab1d609
+size 939525168

model-00016-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf0dc7610e2fc850270c8b3d1287c8e16075a53cf7c6d1465ecbe4cfbae082b
+size 905987688

model-00017-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfda80e67e0ed38b0eb418b998391f90c5cd3bed45770ba80201a71d30d26a68
+size 905987688

model-00018-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7be3d45c2f8207923c9570c8e51be14f6e9e1205fa7007b6aad49d0c0a97fb0
+size 905987688

model-00019-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd725da450955b8c6a7fefc8127c5b1ff07a0412a73518ca16cb846051c8702c
+size 905987688

model-00020-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0169f11937509872f7146c9934cb33ff274941ca0e729d705df7f6df8e8f5da7
+size 939525168

model-00021-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d511a7a42e59c77f17e10f19ad25525d7720943c11f3b8df747a804a6eea9ffb
+size 905987688

model-00022-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02de30dc8124edaa500ecc95d511b9a47d25980b13319972a7ab8aa07187407e
+size 905987688

model-00023-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbbc94fe1edb127989a327ba494727baa1f8364bc8560a95a7278b8cbd4e8312
+size 905987688

model-00024-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c24de878bf16cad14918f0be896649efc6db0a0eed5e8409dcc06e56e17c6d
+size 905987688

model-00025-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37e1dd0a25a5f934673999325efb9439e39fa61a6edf6cd12e5f19e34b11c94d
+size 939525168

model-00026-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56930fa6316f922b558588f293428e832eec3bab343f1c2b84c92f1b59d9f62e
+size 905987688

model-00027-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc0f632df9227416e35d7cb151fabadc40dafcf1c968ebc4f5b53603f6f7722
+size 905987688

model-00028-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1725f916abb63eb65777392900299e2cef430e1f76df34a8d82543069b5989c0
+size 905987688

model-00029-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:330a3841995f08de29ecade5e03f548d4d904d5241da9aa1eed1090dac1a2cad
+size 905987688

model-00030-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e5aaf9b9d29e507d6f04900e70baa87f601beb8dd6f6fc7a0adfa779a145e4
+size 939525168

model-00031-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479cba83d4c5df0f9db6799dcbda383ebeecd3be0e0ecc8451e3cf4de5bc0fda
+size 905987688

model-00032-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f10a8b35939f2dece4394303e84be120a6af22322f6f4204fa3052e0d9f34c98
+size 905987688

model-00033-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17608af1d0359fa6fe0055219991f45c9369bb3ece160d27153a864afd06a7b9
+size 905987688

model-00034-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77b642a5bcc2b1c2951b186549c3ef8e3a41dcd9433cebf052873c9aabd1b09f
+size 905987688

model-00035-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257720df11d81c4e1772b6baca83bab812724bfdcaebceb95724f58c73f79950
+size 939525168

model-00036-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4034f5e72c4e0c8b9406603e746098924076a67b1e31c043ccb8476cbe0f929
+size 905987688

model-00037-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d67f195cce7918243a11eb87fe75678486e04e67632f570af340e8276d6fb683
+size 905987688

model-00038-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52676e8f17048f3817a18dc656f779da105504222cd66ff6a10a2d31cea87883
+size 905987688

model-00039-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fcb47d0f4109cac7c5443c271611d0687b749c503d5f37b1e489066eeb9999e
+size 905987688

model-00040-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257dbd95dbc67c37e6cd1a9a6e08aa9543b82a63a47d0b172816ba50f7e868fc
+size 939525168

model-00041-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60b8dfc84ac1753b81044e50a3671302d59e9070541fc403a60d31d2cfb2e8fe
+size 380383248

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 37032828928}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00041.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00041.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00041.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00041.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00041.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00041.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00041.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00041.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00041.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00041.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00041.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00041.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00041.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00041.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00041.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00041.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00041.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00041.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00041.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00041.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00041.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00041.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00041.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00041.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00041.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00041.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00041.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00041.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00041.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00041.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00041.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00041.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00041.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00041.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00041.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00041.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00041.safetensors", "model.layers.6.input_layernorm.weight": "model-00008-of-00041.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00041.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00041.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00041.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00041.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00041.safetensors", "model.layers.7.input_layernorm.weight": "model-00009-of-00041.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00041.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00041.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00041.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00041.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00041.safetensors", "model.layers.8.input_layernorm.weight": "model-00011-of-00041.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00041.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00011-of-00041.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00011-of-00041.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00041.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00041.safetensors", "model.layers.9.input_layernorm.weight": "model-00012-of-00041.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00012-of-00041.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00012-of-00041.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00012-of-00041.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00012-of-00041.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00041.safetensors", "model.layers.10.input_layernorm.weight": "model-00013-of-00041.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00013-of-00041.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00013-of-00041.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00013-of-00041.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00013-of-00041.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00013-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00041.safetensors", "model.layers.11.input_layernorm.weight": "model-00014-of-00041.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00014-of-00041.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00014-of-00041.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00014-of-00041.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00014-of-00041.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00014-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00041.safetensors", "model.layers.12.input_layernorm.weight": "model-00016-of-00041.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00016-of-00041.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00016-of-00041.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00016-of-00041.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00016-of-00041.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00016-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00041.safetensors", "model.layers.13.input_layernorm.weight": "model-00017-of-00041.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00017-of-00041.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00017-of-00041.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00017-of-00041.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00017-of-00041.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00017-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00041.safetensors", "model.layers.14.input_layernorm.weight": "model-00018-of-00041.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00018-of-00041.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00018-of-00041.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00018-of-00041.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00018-of-00041.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00018-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00041.safetensors", "model.layers.15.input_layernorm.weight": "model-00019-of-00041.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00019-of-00041.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00019-of-00041.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00019-of-00041.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00019-of-00041.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00019-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00041.safetensors", "model.layers.16.input_layernorm.weight": "model-00021-of-00041.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00021-of-00041.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00021-of-00041.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00021-of-00041.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00021-of-00041.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00021-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00041.safetensors", "model.layers.17.input_layernorm.weight": "model-00022-of-00041.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00022-of-00041.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00022-of-00041.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00022-of-00041.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00022-of-00041.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00022-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00041.safetensors", "model.layers.18.input_layernorm.weight": "model-00023-of-00041.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00023-of-00041.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00023-of-00041.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00023-of-00041.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00023-of-00041.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00023-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00041.safetensors", "model.layers.19.input_layernorm.weight": "model-00024-of-00041.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00024-of-00041.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00024-of-00041.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00024-of-00041.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00024-of-00041.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00024-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00041.safetensors", "model.layers.20.input_layernorm.weight": "model-00026-of-00041.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00026-of-00041.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00026-of-00041.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00026-of-00041.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00026-of-00041.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00026-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00026-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00027-of-00041.safetensors", "model.layers.21.input_layernorm.weight": "model-00027-of-00041.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00027-of-00041.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00027-of-00041.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00027-of-00041.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00027-of-00041.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00027-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00041.safetensors", "model.layers.22.input_layernorm.weight": "model-00028-of-00041.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00028-of-00041.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00028-of-00041.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00028-of-00041.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00028-of-00041.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00028-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00029-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00029-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00029-of-00041.safetensors", "model.layers.23.input_layernorm.weight": "model-00029-of-00041.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00029-of-00041.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00029-of-00041.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00029-of-00041.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00029-of-00041.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00029-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00030-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00031-of-00041.safetensors", "model.layers.24.input_layernorm.weight": "model-00031-of-00041.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00031-of-00041.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00031-of-00041.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00031-of-00041.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00031-of-00041.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00031-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00031-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00031-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00041.safetensors", "model.layers.25.input_layernorm.weight": "model-00032-of-00041.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00032-of-00041.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00032-of-00041.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00032-of-00041.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00032-of-00041.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00032-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00032-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00033-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00033-of-00041.safetensors", "model.layers.26.input_layernorm.weight": "model-00033-of-00041.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00033-of-00041.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00033-of-00041.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00033-of-00041.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00033-of-00041.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00033-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00033-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00034-of-00041.safetensors", "model.layers.27.input_layernorm.weight": "model-00034-of-00041.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00034-of-00041.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00034-of-00041.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00034-of-00041.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00034-of-00041.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00034-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00035-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00035-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00041.safetensors", "model.layers.28.input_layernorm.weight": "model-00036-of-00041.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00036-of-00041.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00036-of-00041.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00036-of-00041.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00036-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00036-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00036-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00036-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00037-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00037-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00037-of-00041.safetensors", "model.layers.29.input_layernorm.weight": "model-00037-of-00041.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00037-of-00041.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00037-of-00041.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00037-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00037-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00037-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00038-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00041.safetensors", "model.layers.30.input_layernorm.weight": "model-00038-of-00041.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00038-of-00041.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00038-of-00041.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00038-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00038-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00039-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00039-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00039-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00039-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00039-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00039-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00039-of-00041.safetensors", "model.layers.31.input_layernorm.weight": "model-00039-of-00041.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00039-of-00041.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00039-of-00041.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00039-of-00041.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00039-of-00041.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00039-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00040-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00040-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00040-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00040-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00040-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00040-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00040-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00040-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00041-of-00041.safetensors", "model.norm.weight": "model-00041-of-00041.safetensors", "lm_head.weight": "model-00041-of-00041.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00041-of-00041.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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "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
+}