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": "float16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,9 @@
+
+base_model: BioMistral/BioMistral-7B
+dtype: float16
+gate_mode: random
+experts:
+  - source_model: mistralai/Mistral-7B-Instruct-v0.1
+    positive_prompts: ["You are a helpful medical assistant."]
+  - source_model: mistralai/Mistral-7B-Instruct-v0.3
+    positive_prompts: ["You are assistant for medical question answering."]

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f31fe45eea9f2e04252373a2f6a6e406a403070aee8061fcc1316d06fd47993
+size 933250480

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b80d615244a58da08b3ee80a7e63f868591cd911e0d92ca5278bc53c5d07101
+size 989890808

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56865499731163250a0c5ee675d1072778e3a9fd207e4dcac5ca392ed88cb6fb
+size 905987664

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62c71105738d0d12460464b4b14dc10aa900e9acaddfee73d51c4e8cd5d871a
+size 905987664

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cdbc3dc96a5f65cf5a803477979b9d693f6f2d918c665ea136b4a2f8e176aa8
+size 905987664

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e90f281d00eb2d1fa8d298639ea4db8f6ce35fcb9cd31e02c91b115fb9d966f9
+size 905987664

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8926647775c0b5ae5327713e27febe8e7baab7b92c8006d476d0b213894c9a5c
+size 905987664

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61cec68c22ee9a7e80b60aebae0b27d07552aa0968a3986e560d95792dd24fb0
+size 989890808

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b5e53e83ecdebed3eee14b68c9e7c33abb1f836859badcaf93d4bb55f01fde
+size 905987664

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194f4d98320fb6d6abdcfeff4b835b83caeac8449cc3ad708c54d91b6e37a329
+size 905987672

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f700b5110a4953f4ecf80dfa17cb09d18cb1933485d78b8650f9e15edd54bff9
+size 905987672

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:657773005a8c327abec0bfae8846e4e4cce0ec10896bec84e4d23f369d06d032
+size 905987672

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f51203297f1bb8b2a52c370681695c370799e15d02347b08c4d6e8e92610f089
+size 905987672

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfab05ed84b6f4af288730b12017994bfebf35fa3c665c99cb596c3b0200b57e
+size 989890824

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1114a997fdba3d019fb29c32fcdc4285e28a6c0340138ddd48108320af8a64
+size 905987672

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d9341f4f2af1880aa80f493b9bb3688fe7c77e81501a3cca87936653b17d0fc
+size 905987672

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e02dc78709453d9f201b75df0124bcd0e086eecd6dd072de6b09532d33f5bf6
+size 905987672

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3bcbb4f0fbda854facd80396db52e1de5c1f0633f1d67d0857ad95535de50f
+size 905987672

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f058fae27a1ba90921087ea715a648e7b65135a051d6c6113c259a315819a00c
+size 905987672

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6d64bfb4717b830e5b48910b6053df2a1c7bccf6394f38e1f3d0724799adc6
+size 989890824

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948c19887b44bb348ebb9ed8a1e3b968831387abc9afbdf684f966c8b43ee539
+size 905987672

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ff80eeb20a29c6424084b0244cf85aac6e38f6ea8316c3e5e187a0817ccc55
+size 905987672

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7391ee6086b437a27e55032b010a533c9041f298b8ceb5e4c229ee99d706237e
+size 905987672

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a73d1cb6cc8c1927554c56c38aab46dee1e2f77cc9b1efc2f4bd03ef096373ce
+size 905987672

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c96195a44ca40c72e7cf150747f607394c99bd38a413bd43dfc693424cd03353
+size 905987672

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e940971729a9ee7e5e2f85e6c4270e935c5a06c8b674097bd6dfeb791aaf45e
+size 989890824

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744a29075eb0012505aa3d9d8c363272e51143ceb5bd820333d453554ece3f2d
+size 905987672

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49b23db7a7aec82fb24ec5c3ecf310504ad461de871479a34fcbef97299e16a6
+size 849883632

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
+}