Upload folder using huggingface_hub

xDAN-L1-Edge-4x1.5b-reasoning-pro-0827

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/data/vayu/train/models/xDAN-L1-Edge-1.5b-Reasoning-0825-mmlu-pro-e2",
+  "architectures": [
+    "Qwen2MoeForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "mlp_only_layers": [],
+  "model_type": "qwen2_moe",
+  "moe_intermediate_size": 8960,
+  "norm_topk_prob": true,
+  "num_attention_heads": 12,
+  "num_experts": 4,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 8960,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32772926994a04e375fae323864a4f0f51cd34a088375e4d1bef9510d6b45864
+size 4981002864

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30397691c7afad2a0a071472b0fe935977b068a5c311e1b3103aafd48d5a7cd7
+size 4976698912

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f38fc3a7bf4fd014bc3def026c8c059cf67fc76b56c1b1aad836a8bdd6bee01
+size 2845432344

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 12803046400}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.shared_expert.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.shared_expert.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.shared_expert.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.shared_expert.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.experts.0.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.experts.1.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.experts.2.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.experts.3.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.shared_expert.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.experts.0.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.experts.1.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.experts.2.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.experts.3.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.shared_expert.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.experts.0.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.experts.1.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.experts.2.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.experts.3.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.shared_expert.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.experts.0.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.experts.1.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.experts.2.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.experts.3.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.shared_expert.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.experts.0.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.experts.1.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.experts.2.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.experts.3.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.shared_expert.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.experts.0.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.experts.1.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.experts.2.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.experts.3.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.shared_expert.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.experts.0.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.experts.1.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.experts.2.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.experts.3.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.shared_expert.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.experts.0.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.experts.1.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.experts.2.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.experts.3.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.shared_expert.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.experts.0.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.experts.1.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.experts.2.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.experts.3.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.shared_expert.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.experts.0.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.experts.1.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.experts.2.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.experts.3.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.shared_expert.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.experts.0.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.experts.1.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.experts.2.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.experts.3.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.shared_expert.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.norm.weight": "model-00003-of-00003.safetensors", "lm_head.weight": "model-00003-of-00003.safetensors", "model.layers.0.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.0.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.1.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.1.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.2.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.2.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.3.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.3.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.4.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.4.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.10.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.10.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.11.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.11.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.12.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.12.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.13.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.13.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.14.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.14.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.15.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.15.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.16.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.16.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.17.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.17.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.18.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.18.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.19.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.19.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.20.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.20.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.21.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.21.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.22.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.23.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.24.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.gate.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.shared_expert_gate.weight": "model-00003-of-00003.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|im_end|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}