Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,34 @@
+{
+  "<pad10>": 32010,
+  "<pad11>": 32011,
+  "<pad12>": 32012,
+  "<pad13>": 32013,
+  "<pad14>": 32014,
+  "<pad15>": 32015,
+  "<pad16>": 32016,
+  "<pad17>": 32017,
+  "<pad18>": 32018,
+  "<pad19>": 32019,
+  "<pad20>": 32020,
+  "<pad21>": 32021,
+  "<pad22>": 32022,
+  "<pad23>": 32023,
+  "<pad24>": 32024,
+  "<pad25>": 32025,
+  "<pad26>": 32026,
+  "<pad27>": 32027,
+  "<pad28>": 32028,
+  "<pad29>": 32029,
+  "<pad2>": 32002,
+  "<pad30>": 32030,
+  "<pad31>": 32031,
+  "<pad3>": 32003,
+  "<pad4>": 32004,
+  "<pad5>": 32005,
+  "<pad6>": 32006,
+  "<pad7>": 32007,
+  "<pad8>": 32008,
+  "<pad9>": 32009,
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "NousResearch/Hermes-2-Pro-Mistral-7B",
+  "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": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 3,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": false,
+  "vocab_size": 32032
+}

mergekit_moe_config.yml

@@ -0,0 +1,53 @@
+
+base_model: NousResearch/Hermes-2-Pro-Mistral-7B
+architecture: mixtral
+experts:
+  - source_model: NousResearch/Hermes-2-Pro-Mistral-7B
+    positive_prompts:
+    - "chat"
+    - "assistant"
+    - "tell me"
+    - "explain"
+    - "I want"
+    - "help me understand"
+    - "provide information on"
+    - "describe"
+    - "what is"
+    - "how to"
+  - source_model: beowolx/MistralHermes-CodePro-7B-v1
+    positive_prompts:
+    - "code"
+    - "python"
+    - "javascript"
+    - "programming"
+    - "algorithm"
+    - "develop"
+    - "debug"
+    - "optimize"
+    - "implement"
+    - "software"
+  - source_model: nvidia/OpenMath-Mistral-7B-v0.1-hf
+    positive_prompts:
+    - "equation"
+    - "calculate"
+    - "calculating"
+    - "geometry"
+    - "mathematical proof"
+    - "derive"
+    - "solve"
+    - "integral"
+    - "differential"
+    - "theorem"
+    - "algebra"
+    - "linear algebra"
+    - "matrix"
+    - "vector"
+    - "calculus"
+    - "limit"
+    - "derivative"
+    - "integration"
+    - "statistics"
+    - "probability"
+    - "discrete math"
+    - "number theory"
+    - "combinatorics"

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c6affa95978d26423c1c01b02ec1ecd7491f46900ce54951a622bbc2538f0e
+size 4909785232

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14f28333f7e29d015df3d83e15403011e7468ac38f72f3217e10469e857a7267
+size 4915797744

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1f44cd47148e7c47ddbf5aad570eee74128c5cda3637e8e3e426ff1372ce73
+size 4915797792

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:968f6d54b2abcd48cd3c5b653b6c9539fc89e0d938ef04986d60fbd8c524a18f
+size 4999700976

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf5df88584101b2701c63359292da11fafa41d840a0b21f129224730a60fca8
+size 4915797808

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a95d649ce98e96f868ae2246cd969c0bc8c7d37ab4e529512f9de00deff6fd2f
+size 4915797808

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb544575d783b7c8e8de56c0e1acd791e685ef715783381a330f5d5d6fddb134
+size 4999700976

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75f131960b8f33fa25b27a1de850f2fe3ed9543f7dd65340c99bc69966fcbc1e
+size 2461039520

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 37033353216}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.safetensors", "lm_head.weight": "model-00008-of-00008.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,310 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "<pad2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "<pad3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "<pad4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "<pad5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "<pad6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "<pad7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "<pad8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "<pad9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "<pad10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "<pad11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "<pad12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<pad13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32014": {
+      "content": "<pad14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32015": {
+      "content": "<pad15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<pad16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<pad17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<pad19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<pad20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<pad21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32022": {
+      "content": "<pad22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32023": {
+      "content": "<pad23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32024": {
+      "content": "<pad24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32025": {
+      "content": "<pad25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32026": {
+      "content": "<pad26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32027": {
+      "content": "<pad27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32028": {
+      "content": "<pad28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32029": {
+      "content": "<pad29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32030": {
+      "content": "<pad30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32031": {
+      "content": "<pad31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": [
+    {
+      "name": "default",
+      "template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+    },
+    {
+      "name": "tool_use",
+      "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n    \"string\": \"str\",\n    \"number\": \"float\",\n    \"integer\": \"int\",\n    \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n    {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n    {{- \"list[\" +  json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n    {%- if json_spec.additionalProperties is defined %}\n        {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n    {%- else %}\n        {{- \"dict\" }}\n    {%- endif %}\n{%- elif json_spec.type is iterable %}\n    {{- \"Union[\" }}\n    {%- for t in json_spec.type %}\n      {{- json_to_python_type({\"type\": t}) }}\n      {%- if not loop.last %}\n        {{- \",\" }} \n    {%- endif %}\n    {%- endfor %}\n    {{- \"]\" }}\n{%- else %}\n    {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n    {%- if tool.function is defined %}\n        {%- set tool = tool.function %}\n    {%- endif %}\n    {{- '{\"type\": \"function\", \"function\": ' }}\n    {{- '{\"name\": ' + tool.name + '\", ' }}\n    {{- '\"description\": \"' + tool.name + '(' }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {{- param_name + \": \" + json_to_python_type(param_fields) }}\n        {%- if not loop.last %}\n            {{- \", \" }}\n        {%- endif %}\n    {%- endfor %}\n    {{- \")\" }}\n    {%- if tool.return is defined %}\n        {{- \" -> \" + json_to_python_type(tool.return) }}\n    {%- endif %}\n    {{- \" - \" + tool.description + \"\\n\\n\" }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {%- if loop.first %}\n            {{- \"    Args:\\n\" }}\n        {%- endif %}\n        {{- \"        \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n    {%- endfor %}\n    {%- if tool.return is defined and tool.return.description is defined %}\n        {{- \"\\n    Returns:\\n        \" + tool.return.description }}\n    {%- endif %}\n    {{- '\"' }}\n    {{- ', \"parameters\": ' }}\n    {%- if tool.parameters.properties | length == 0 %}\n        {{- \"{}\" }}\n    {%- else %}\n        {{- tool.parameters|tojson }}\n    {%- endif %}\n    {{- \"}\" }}\n    {%- if not loop.last %}\n        {{- \"\\n\" }}\n    {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}, \"name\": {\"title\": \"Name\", \"type\": \"string\"}}, \"required\": [\"arguments\", \"name\"], \"title\": \"FunctionCall\", \"type\": \"object\"}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"arguments\": <args-dict>, \"name\": <function-name>}\n' }}\n{{- '</tool_call><|im_end|>' }}\n{%- for message in messages %}\n    {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n<tool_call>\\n' }}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '{ ' }}\n            {%- if tool_call.arguments is defined %}\n                {{- '\"arguments\": ' }}\n                {{- tool_call.arguments|tojson }}\n                {{- ', '}}\n            {%- endif %}\n            {{- '\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\"}' }}\n            {{- '\\n</tool_call> ' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if not message.name is defined %}\n            {{- raise_exception(\"Tool response dicts require a 'name' key indicating the name of the called function!\") }}\n        {%- endif %}\n        {{- '<|im_start|>' + message.role + '\\n<tool_response>\\n' }}\n        {{- '{\"name\": \"' }}\n        {{- message.name }}\n        {{- '\", \"content\": ' }}\n        {{- message.content|tojson + '}' }}\n        {{- '\\n</tool_response> <|im_end|>\\n' }} \n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+    }
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}