Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BioMistral/BioMistral-7B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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": 2,
+  "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": "4.45.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,11 @@
+base_model: BioMistral/BioMistral-7B
+gate_mode: approach # one of "hidden", "cheap_embed", or "random"
+dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
+experts:
+  - source_model: Treza12/BioMistral-7B-F0
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Diagnosis"
+  - source_model: cognitivecomputations/WestLake-7B-v2-laser
+    positive_prompts:
+      - "Answer this question from the Winogrande test."
+      - "Use advanced knowledge of culture and humanity"

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd587e1729a4ca6efa4a692c5b03c7bd465f20e5247f9b489d5c25c00628965c
+size 933250496

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa66b2d356e88c655d9033f1d7fc5b4ccce6a07dcc1b7432a43f89a6fa1e9c2a
+size 989890824

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95955f60b7f2bd81cb4906691d409d3f6b3881c0ccda73b84bbf79ec78fb00e0
+size 905987672

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e7dabc7132eeee12cd1968c6caefbfbae5f8a224469604594c2b0b4c068dec
+size 905987672

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e8f82f70ed8ab07c9f956c2364d3711568a199f067020ef82749dd5b5d2d99
+size 905987672

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aae8e95437b3355fe3fdc92fb3e2c99ab093ef6c90bf7c683df1886002c45d8
+size 905987672

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0e6233978977890b6da0e515111a0a749ee5377e142699767d07c58c98ccd2d
+size 905987672

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1c564fe4b49ebb1bb916ed73dc43f3224041bde8ba90336ea4bd370c2b2b43
+size 989890824

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:232b90a3769ae56f2a6d64baca1d6c10423f107f8a91da13f38d4b55899ba6b5
+size 905987680

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c1c68efb6409e47f2c1e6c8d31b0f91bfb70fe72132c9c507785dd2874d44d
+size 905987688

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a3b55cec3a7871ac36933fe624aaf80dae1299a910ec7504853cbdaebaa466
+size 905987688

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3e51981b4a3621ef0870ba0f81f6cd6e2a0024de62304c0d2f0a65d03a71be
+size 905987688

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec9033a4bfb211347332c9cd60c66c330f110baca4ccc71728f4d9ca7bd9c6e2
+size 905987688

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d249572ef355c1398fa0991ed3eebec659ca507d3a4e4715045f0cd5bee52aca
+size 989890840

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef60ffef20401166b19dd5d598558c77064ca784a691cc8610b0360ca3fcf59
+size 905987688

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3804a8e3941246627d2e3cfd3954301f4376337485b0729291789e950975b84f
+size 905987688

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c4c026d1383160b1f0ee93e04c9f835db1bf794d3a44f4041d53fe15b81e02
+size 905987688

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc535bca2539f2ac2c3e6618e400b8c1bc7146188940b81ff7c1d1964bb8c29
+size 905987688

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37583a0abafe97519fabcd91f772f60ef6768084a90d5d2cfab7cf917abff741
+size 905987688

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c389d1acb273a3be80ec51f3625f410b333c9daba17f1be14ac7b15313b27588
+size 989890840

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c218260ad571523595121a082db9a34bf53fb07191c8b3411a9c28df4b1e4b0
+size 905987688

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5710a468e2c815a6c0a0ad18c9694d23d8b6877c2b8229d483a9ad2e60d2a5
+size 905987688

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248a50011b8f9e2f0aa838c7815a4f394bb69556d00192e6de09eba5f1a11146
+size 905987688

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b711ba244d13836a18855b4c6db3452f496171a207d010fd3ffc325dd8b823dc
+size 905987688

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb2a7389c068e64d3d938fe1d3a54f0ae294a7f94b035ce2cd9b9e72d8030444
+size 905987688

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88f7c211791608ab2c4ad7fae29a39af1da7a6914f7ea47a929d150ba1323ec2
+size 989890840

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a29943cbd842690d4d1b0c03bf9bf421873280bb1bbf7d25fe06770d840b92
+size 905987688

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb5b29a4775db0c4b6d20dfec7c9ac2f1515a74112acbb2812973c215a4c864
+size 849883672

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 25758277632}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00028.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00028.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00028.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00028.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00028.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00028.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00028.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00028.safetensors", "model.layers.7.input_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00028.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00028.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00028.safetensors", "model.layers.10.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00028.safetensors", "model.layers.11.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00028.safetensors", "model.layers.12.input_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00028.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00028.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00028.safetensors", "model.layers.13.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00028.safetensors", "model.layers.14.input_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00013-of-00028.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00028.safetensors", "model.layers.15.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00028.safetensors", "model.layers.16.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00028.safetensors", "model.layers.17.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00028.safetensors", "model.layers.18.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00028.safetensors", "model.layers.19.input_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00017-of-00028.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00028.safetensors", "model.layers.20.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00028.safetensors", "model.layers.21.input_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00019-of-00028.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00019-of-00028.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00028.safetensors", "model.layers.22.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00028.safetensors", "model.layers.23.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00028.safetensors", "model.layers.24.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00028.safetensors", "model.layers.25.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00028.safetensors", "model.layers.26.input_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00023-of-00028.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00023-of-00028.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00023-of-00028.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00028.safetensors", "model.layers.27.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00028.safetensors", "model.layers.28.input_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00025-of-00028.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00028.safetensors", "model.layers.29.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00028.safetensors", "model.layers.30.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00028.safetensors", "model.layers.31.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00028.safetensors", "model.norm.weight": "model-00028-of-00028.safetensors", "lm_head.weight": "model-00028-of-00028.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors"}}

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}