Upload 31 files

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542fc77373389591ddf7ea8ce2382434b60ea41aff2fa76c297d259c0ed08930
+size 1929415992

model-00003-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057287a108c310d0c5849b7fc4cad294a4412a9b70a667b6e0d821bd302f0be7
+size 1962953472

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29473e46956ca964903829d1688069f12a094325ff6e3812f38e93737052d6d8
+size 1962953472

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a26480738dfdff093bc0061422e8a78a0bfcf0a98e1db5f9372d21eacb9ad18
+size 1929415992

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7e8da98119de90472f0b4cc2fee4250af8dc0d5064504a2a96b12790e13e3b3
+size 1962953472

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1e6f7cdbdf7a54fe5ea80cb92ac5883df3ef882bae53b3deac7f9f3f536727
+size 1962953472

model-00008-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596c62c52b3da0ef1ce6972c590d390eab4c74e74c63b3be4bfb39b889cb6777
+size 1929415960

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bfd5c5d510f42eb4594b45c0092343e6a28e6965f854096aa13e9d8661b0d89
+size 1962953488

model-00010-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f00f133de329dcdd0b3cb6ef45d45ba775b55e63bc96df0aa40c70d9d487872
+size 1962953488

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46fbb02656929ef36551713efbd0b2a9f5c4264791c36a46e8545a3d3e8cb3bd
+size 1996516344

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e169d574c92f8ad4d5fc97e5e0931b60bc9f1dc0c3191f8172f057b474ac4099
+size 1895853160

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:037de00170aeac5a4d6fcdca5a57ece9609d41ebf6d3a2517caad834b34067bb
+size 1962953488

model-00014-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858d5c2f0aa5eec42ba1d65b7c2f8c5cc439f0771d5be139c93352cc4185c9db
+size 1962953488

model-00015-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda22d75b91337e585b680ab3d53612c340cbad8479d38232a53ac2b04eb7d89
+size 1929416016

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b07e5450ccee309d565f874eadced2a345d31b6adfc5d7ea61a480af1bb7735
+size 1962953488

model-00017-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c35e48828bccbdfe8d036fc86e93b1313d24c93841a3501cf92b2b18b2ad8f2
+size 1962953488

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03df0be00d6718604c332992ad5cfd638480810f3625a3648e7f92271c1cfb6b
+size 1929416016

model-00019-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ce5a22dac877c420566672431da19746075e440c3fb0b9f72c913d14162f50
+size 1962953488

model-00020-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:235e6d3eba7c0cfe64d26e76b9bc97095f613258a942b1b258a6126a7f78006d
+size 1962953488

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef186e961ea991517db70677313a62961a2069b16528ca85424311a16e4268c
+size 1929416016

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03925a3f3fa30a415744a104bab52b0641c29480333719777a5a481e8ace3cf4
+size 1962953488

model-00023-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2d66a0533e391e84598375a5e1d47544dc4c24fa6feed97c22ad78906830dd6
+size 1962953488

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56de581e627666b4a6df96b02fc70c07f7ce4b043515d5e7e79a63da573cc97
+size 1996516344

model-00025-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13898226d7d26e8f0ed4510fd5d6b8d3842a71b4e32c82eb72a76f091d16dcf0
+size 1460680264

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00025.safetensors", "model.norm.weight": "model-00001-of-00025.safetensors", "lm_head.weight": "model-00001-of-00025.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00025.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00025.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00025.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00025.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00025.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00025.safetensors", "model.layers.8.input_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00025.safetensors", "model.layers.10.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.11.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00025.safetensors", "model.layers.12.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00025.safetensors", "model.layers.15.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.16.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.19.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00025.safetensors", "model.layers.20.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00025.safetensors", "model.layers.21.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00025.safetensors", "model.layers.23.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00025.safetensors", "model.layers.24.input_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00025.safetensors", "model.layers.25.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00025.safetensors", "model.layers.27.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00025.safetensors", "model.layers.28.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00025.safetensors", "model.layers.29.input_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00025.safetensors", "model.layers.31.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00025.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00025-of-00025.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 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+}