Upload folder using huggingface_hub

config.json

@@ -1,10 +1,11 @@
 {
   "architectures": [
-    "MixtralForCausalLM"
+    "Qwen2MoeForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 31989,
+  "decoder_sparse_step": 1,
   "eos_token_id": 31989,
   "head_dim": 64,
   "hidden_act": "silu",
@@ -12,25 +13,31 @@
   "initializer_range": 0.036084391824351615,
   "intermediate_size": 1920,
   "max_position_embeddings": 8192,
+  "max_window_layers": 28,
   "mlp_bias": false,
-  "model_type": "mixtral",
+  "mlp_only_layers": [],
+  "model_type": "qwen2_moe",
+  "moe_intermediate_size": 1920,
+  "norm_topk_prob": true,
   "num_attention_heads": 12,
+  "num_experts": 3,
   "num_experts_per_tok": 2,
   "num_hidden_layers": 27,
   "num_key_value_heads": 4,
-  "num_local_experts": 4,
   "output_router_logits": false,
   "pad_token_id": 31989,
   "pretraining_tp": 1,
+  "qkv_bias": true,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "router_aux_loss_coef": 0.001,
-  "router_jitter_noise": 0.0,
+  "shared_expert_intermediate_size": 1920,
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.53.3",
   "use_cache": false,
+  "use_sliding_window": false,
   "vocab_size": 32000
 }

mergekit_moe_config.yml

@@ -1,6 +1,7 @@
 base_model: minpeter/tiny-ko-187m-base-250725
 gate_mode: hidden
 dtype: bfloat16
+architecture: qwen
 experts:
   - source_model: minpeter/tiny-ko-187m-base-250725
     positive_prompts:
@@ -14,6 +15,7 @@ experts:
       - "[Genres: Science Fiction]\n[Tags: humor, old school, sci fi]"
       - "> get ye flask"
       - "[Mode: Interactive Storyteller]"
+shared_experts:
   - source_model: minpeter/tiny-ko-187m-base-250725
     positive_prompts:
       - "<|im_start|>user\nWie geht es dir?<|im_end|>"

model-00001-of-00001.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1265c116b469ee3032ca93a959eb6e608c864e094e905c3533e1e89c4770e2f4
-size 1089915064
+oid sha256:7c6f18b44ce328ef35438c1da95654bf1fe7dbb0982377d80d7c516d9ba0dd7a
+size 1089993904

model.safetensors.index.json

@@ -1 +1 @@
-{"metadata": {"mergekit_version": "0.0.6", "total_size": 1089851904}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors"}}
+{"metadata": {"mergekit_version": "0.0.6", "total_size": 1089921024}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -1,5 +1,17 @@
 {
-  "eos_token": "<|endoftext|>",
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,7 +1,14 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Left",
+    "pad_to_multiple_of": null,
+    "pad_id": 31989,
+    "pad_type_id": 0,
+    "pad_token": "<|endoftext|>"
+  },
   "added_tokens": [
     {
       "id": 31989,
@@ -10,7 +17,7 @@
       "lstrip": false,
       "rstrip": false,
       "normalized": true,
-      "special": false
+      "special": true
     },
     {
       "id": 31990,

tokenizer_config.json

@@ -8,7 +8,7 @@
       "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "31990": {
       "content": "<|im_start|>",