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": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32002
+}

mergekit_moe_config.yml

@@ -0,0 +1,30 @@
+
+base_model: openchat/openchat-3.5-0106
+dtype: bfloat16
+gate_mode: hidden
+experts:
+  - source_model: openchat/openchat-3.5-0106
+    positive_prompts:
+       - "Hello!"
+       - "Who are you?"
+       - "I would want to visit Paris. What do you think?"
+    negative_prompts:
+       - "Give me a python code for the fastest sorting algorithm."
+       - "Tell me what's 8 to the power of 19."
+  - source_model: m-a-p/OpenCodeInterpreter-DS-6.7B
+    positive_prompts:
+       - "Write me a java code for the fibonacci array."
+       - "I have an error in my python code."
+    negative_prompts:
+       - "Give me some tourism advices."
+       - "Write me poetry."
+       - "Tell me the result of 2 divided by 0.333"
+  - source_model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
+    positive_prompts:
+       - "Tell me what is 2 times 46 equal?"
+       - "4 to the power of 62 is?"
+    negative_prompts:
+       - "Give me a recipe for spaghetti."
+       - "What locstions to you suggest visiting?"
+       - "Write me a simple cpp code."
+

model-00001-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba57c61e30a4b81520d2c3acf5073a84f02d180a06938f2da56f3ffcabe8b220
+size 1942271440

model-00002-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ba0b9aace2c9685c356a241edf86511da786fc8a4a5e47a1ddbde2da423084
+size 1950353736

model-00003-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd42da3a01da8ff07b9e37a1750941259fcd66b11e03b3061ad11444766e85a
+size 1950353752

model-00004-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41c31323d521063d11f05d0e1f5d0097e075f6ccb393564d826a0e7b5bbf3d5
+size 1950353752

model-00005-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707093294aa14dd75512eb932567cd07d4e2234d968fa0ad57ef89756e23faec
+size 1950353752

model-00006-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d36ef33e8cbd53c5ad9c515e3f1deabc21d972a2eb38c88b5d5611dd87a6ba
+size 1950353744

model-00007-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d968b97e6057d9746f4444ed8cc4a84c36be927f3bafaba126e43829d8af22
+size 1950353736

model-00008-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aff616ad853d8cd83cefa5d680484e476d9945b05e80ac317b8f150cc7cbfb1
+size 1950353744

model-00009-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9312c48356951405cee95105d57f4fb8f9a9416daae07e7fd4b40bd19f2d3c
+size 1950353752

model-00010-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80cfde4ddea17dc0bd15c7410c454fadd27b22585fa0196f5989b6ca0dbfacf5
+size 1950353752

model-00011-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e98e41e1cf4a5a8b4a7470e8a9cd2068ee50ac5107df71fc98a4d830ba2d11eb
+size 1950353752

model-00012-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b941ca476fc40760091289d9e3813695a006bedd91a67b38beb2af22091834f7
+size 1950353736

model-00013-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ba5c45eee02f652f6d6c3e38efb4ee1d96813d3ea22e4c140d74e122f909a20
+size 1950353744

model-00014-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d1583fdd8d28db97f961a7d305eee48d106fc9bf91cdc3ff210c93109ac7bfd
+size 1950353752

model-00015-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1f2ad8157d04d9637eb311d128f2942303a8f7e65a97abaa31177aec694521d
+size 1950353752

model-00016-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3ae49d366d1e8a9690144b672198697deb8cc7123e32647e6f374d7a5a1b31
+size 1950353752

model-00017-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c42a7000c443feb223a64922070a234537885e2bd13773a43278a30a472e60
+size 1992570104

model-00018-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afab64f44b051569332953e8c241fa4a71a1963f462cd067a6f09b7eaa9816a5
+size 1225532800

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
+}