Upload folder using huggingface_hub

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "yanolja/KoSOLAR-10.7B-v0.2",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.0",
+  "use_cache": false,
+  "vocab_size": 40960
+}

mergekit_moe_config.yml

@@ -0,0 +1,10 @@
+
+base_model: yanolja/KoSOLAR-10.7B-v0.2
+dtype: float16
+experts:
+  - source_model: yanolja/KoSOLAR-10.7B-v0.2
+    positive_prompts: ["당신은 사람들에게 도움을 주는 어시스턴트이다."]
+  - source_model: yanolja/Bookworm-10.7B-v0.4-DPO
+    positive_prompts: ["당신은 다방면으로 답변을 잘하는 어시스턴트이다."]
+gate_mode: cheap_embed
+tokenizer_source: base

model-00001-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60802e3cb96072bdaa2c43bd45c6c370e12400f840f01797bb3f3337e918c4be
+size 1963342736

model-00002-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dd870a597ec2f86dec0885a992ca3d3780e061c9ff1dbc5b46c9cbfb343ffef
+size 1996490944

model-00003-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01cb66b256154f9e71b844f3e2a5f5fead13b992dcd8de8e0a879b19d004e64
+size 1996490952

model-00004-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc55a7a98563268e08159a6d984af309f37a6598e2d55bc61713e066053a1aa
+size 1996490952

model-00005-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a31fd87c82631b1ac83a3f301820f2c401f3c0d1b18efe6469940157f96ae842
+size 1996490952

model-00006-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f75a01f2eec7bfba0e4bbafedbcba4a3d241ddc3dd91a43b03712fbcc148cc8
+size 1996490952

model-00007-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:868961be8a2926748de3e394ba3811c6ac4b893eaa3ec3157c61bc34feddd889
+size 1996490936

model-00008-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f14cc3fbe3ef9c96bc98a0f3d20eaf5098d9a9565a007ce5129a873eb54cf9c1
+size 1996490944

model-00009-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b0b32d3e41ace89381e3632552c561ffc1e51e4eb369c4e150997cf456041fc
+size 1996490952

model-00010-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9128cd94d5ef997205be047ebfa5558e4326fe84f3c33f89c099fa625f9d3afd
+size 1996490952

model-00011-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:990c57900ec7f5278f89f60da8eee393599ca65c6b0e59f1cc125589abe2f8c8
+size 1996490952

model-00012-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c851503b5ea368a367c77866806fd01861b1a546160f0721d7150869b5415c
+size 1996490944

model-00013-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae7772a428d99cdd5e6993ac7e859d7bc0ff84209136101f481c3f3e70a0099b
+size 1996490936

model-00014-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cdc17c53eecfd9b4f6d1c50c86e4a669412aa04dea144f17e559fd3f5b36b28
+size 1996490952

model-00015-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d35e6a0e8fbfd11625d010499303ce6d4d243bfa623b951df92b55a46deaa38a
+size 1996490952

model-00016-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a02f523e625327473b58a13577ad2362bb4591a82669c54a4f130aa77393f6
+size 1996490952

model-00017-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee1d563d3d428dccca97cd0403736f52cb9ca7717183841aeba10da9fc5a05c
+size 1996490952

model-00018-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac87eeef1cc25a52e9f723fd661bc9ac91b6c19568fee1097888e4b9c588d2f
+size 1996893128

model-00019-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a51a9121e5703d29508e19bc08dd2f5c0f37628a8bc20e5aeb5184756e877509
+size 1979726688

model-00020-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2b0ddaf0ceab9195685e097fffd12e1c5e70b03611871c5b9e2eb147f67423
+size 638328304

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00020.safetensors", "model.norm.weight": "model-00001-of-00020.safetensors", "lm_head.weight": "model-00001-of-00020.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00020-of-00020.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": "<|im_end|>",
+    "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_config.json

@@ -0,0 +1,52 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}