Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|end_of_turn|>": 32000,
+  "<|pad_0|>": 32001
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "openchat/openchat-3.5-0106",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "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": 8192,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 3,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32002
+}

mergekit_moe_config.yml

@@ -0,0 +1,12 @@
+
+base_model: openchat/openchat-3.5-0106
+dtype: float16
+gate_mode: cheap_embed
+experts:
+  - source_model: openchat/openchat-3.5-0106
+    positive_prompts: ["You are an helpful general-pupose assistant."]
+  - source_model: m-a-p/OpenCodeInterpreter-DS-6.7B
+    positive_prompts: ["You are helpful coding assistant."]
+  - source_model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
+    positive_prompts: ["You are an assistant good at math."]
+

model-00001-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d02707842d52354592bedd3e9bb0e522c3ba2eab15093992f663574b07dd6f
+size 1942271392

model-00002-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d51a0d1c38b50d3a9ad62a072cdeacd12edf9cdcceff1e22fe5de03ad1cad10e
+size 1950353720

model-00003-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c9aa89c40c2c95dd906365aa2f81100c06ff4da18610687281ced926981257
+size 1950353736

model-00004-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243aa4b97200dfe0c2c3b352e1ade88c4f267d998b3e464ce9cd5ae1507f6613
+size 1950353736

model-00005-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b33da3149b69c294974ffe67bebfddd255df8bce727f67dba5b42c5735d74940
+size 1950353736

model-00006-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e224acdfc51fb09ad820d932da8b4a63a05e56b5400985b0dc93b123c66c55d
+size 1950353728

model-00007-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d5062061b3385104b6c8fc6602fe7f4ed933acfc3fdbdefc7652538b013483
+size 1950353712

model-00008-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99f934502d859b287191446a2c69428ed7f9fbfdb487eeda66efe97819c283e0
+size 1950353728

model-00009-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae462fa58aa88e863501d6e7a630ee64591e952ea8853c83c4dd5a2d556a6a20
+size 1950353736

model-00010-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555f48548d19b56540e73239a247014d417620922618b0ca6b49142ceece1a55
+size 1950353736

model-00011-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8531e0551e446c1a5466ce13018e2b43f0d2baaf44ee88d6bcd0f2b4e5632716
+size 1950353736

model-00012-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b17f18c802527566646c84e2f56a4a9a1df2df94cffd56dfdac613f9f7c27177
+size 1950353712

model-00013-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a460c4d319e56bd924e63f16bbaa78619a4f0b0704e6b6fc5cfb728b5afd08
+size 1950353720

model-00014-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812d00a0b80b1c1ed6926dc2df6bdbda64dac96b1cd156074662c63001d97752
+size 1950353736

model-00015-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a99ddea2882a8e8dae65ea75bcfae200c3cee86047c407aebaeadee51db5c32
+size 1950353736

model-00016-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad83ef19d755843eb952900915cb5065abc686ff0de3d463a9fa740ab85848b
+size 1950353736

model-00017-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a2be9cdd26f83d6e0bf48d0c77dbceaf324103ee25d183b6e845e2ff227b704
+size 1992569984

model-00018-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a683a9b452615e9022ed4aaab856736c986104d801b1ec40489cca3401ec295
+size 1225532720

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00018.safetensors", "model.norm.weight": "model-00001-of-00018.safetensors", "lm_head.weight": "model-00001-of-00018.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00018.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00018.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00018.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00018.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00018.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00018.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00018.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00018.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00018.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00018.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00018.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00018.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00018.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00018.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00018.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00018.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00018.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00018.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00018.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00018.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00018.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00018.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00018.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00018.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00018.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00018.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00018.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00018.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00018.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00018.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00018.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00018.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00018.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00018.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00018.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00018.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00018.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00018.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00018.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00018.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00018.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00018.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00018.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00018.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00018.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00018.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00018.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00018.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00018.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00018.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00018.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00018.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00018.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00018.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00018.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00018.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00018.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00018.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00018.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00018.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00018.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00018.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00018.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00018.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00018.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00018.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00018.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00018.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00018.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00018.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00018.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00018.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00018.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00018.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00018.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00018.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00018.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00018.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00018.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00018.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00018.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00018.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00018.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00018.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00018.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00018.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00018.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00018.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00018.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00018.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00018.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00018.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00018.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00018.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00018.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00018.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00018.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00018.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00018.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00018.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00018.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00018.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00018.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00018.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00018.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00018.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00018.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00018.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00018.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00018.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00018.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00018.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00018.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00018.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00018.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00018.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00018.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00018.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00018.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00018.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00018.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00018.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00018.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00018.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00018.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00018.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00018.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00018.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00018.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00018.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00018.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00018.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00018.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00018.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00018.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00018.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00018.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00018.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00018.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00018.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00018.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00018.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00018.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00018.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00018.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00018.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00018.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00018.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00018.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00018.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00018.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00018.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00018.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00018.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00018.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00018.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00018.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00018.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00018.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00018.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00018.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00018.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00018.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00018.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00018.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00018.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00018.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00018.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00018.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00018.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00018.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00018.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00018.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00018.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00018.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00018.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00018.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00018.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00018.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00018.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00018.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00018.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00018.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00018.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00018.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00018.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00018.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00018.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00018.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00018.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00018.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00018.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00018.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00018.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00018.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00018.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00018.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00018.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00018.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00018.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00018.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00018.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00018.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00018.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00018.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00018.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00018.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00018.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00018.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00018.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00018.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00018.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00018.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00018.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00018.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00018.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00018.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00018.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00018.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00018.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00018.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00018.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00018.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00018.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00018.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00018.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00018.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00018.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00018.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00018.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00018.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00018.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00018.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00018.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00018.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00018.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00018.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00018.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00018.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00018.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00018.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00018.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00018.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00018.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00018.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00018.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00018.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00018.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00018.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00018.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00018.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00018.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00018.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00018.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00018.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00018.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00018.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00018.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00018.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00018.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00018.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00018.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00018.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00018.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00018.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00018.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00018.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00018.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00018.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00018.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00018.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00018.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00018.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00018.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00018.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00018.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00018.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00018.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00018.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00018.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00018.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00018.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00018.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00018.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00018.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00018.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00018.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00018.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00018.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00017-of-00018.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00018.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00017-of-00018.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00018-of-00018.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00018-of-00018.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00018-of-00018.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_turn|>",
+    "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 +1,62 @@
+{
+  "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": "<|end_of_turn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|pad_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_turn|>",
+  "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": true
+}