Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1745846650

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,726 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 65536,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "pad_token_id": 151643,
+  "qkv_bias": false,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "modules_to_not_convert": [
+      "lm_head",
+      "model.layers.0.input_layernorm",
+      "model.layers.0.mlp.gate",
+      "model.layers.0.mlp.shared_expert_gate",
+      "model.layers.0.post_attention_layernorm",
+      "model.layers.0.self_attn.k_proj.bias",
+      "model.layers.0.self_attn.q_proj.bias",
+      "model.layers.0.self_attn.v_proj.bias",
+      "model.layers.1.input_layernorm",
+      "model.layers.1.mlp.gate",
+      "model.layers.1.post_attention_layernorm",
+      "model.layers.1.self_attn.k_proj.bias",
+      "model.layers.1.self_attn.q_proj.bias",
+      "model.layers.1.self_attn.v_proj.bias",
+      "model.layers.1.mlp.shared_expert_gate",
+      "model.layers.2.mlp.shared_expert_gate",
+      "model.layers.2.input_layernorm",
+      "model.layers.2.mlp.gate",
+      "model.layers.2.post_attention_layernorm",
+      "model.layers.2.self_attn.k_proj.bias",
+      "model.layers.2.self_attn.q_proj.bias",
+      "model.layers.2.self_attn.v_proj.bias",
+      "model.layers.3.input_layernorm",
+      "model.layers.3.mlp.gate",
+      "model.layers.3.mlp.shared_expert_gate",
+      "model.layers.3.post_attention_layernorm",
+      "model.layers.3.self_attn.k_proj.bias",
+      "model.layers.3.self_attn.q_proj.bias",
+      "model.layers.3.self_attn.v_proj.bias",
+      "model.layers.4.input_layernorm",
+      "model.layers.4.mlp.gate",
+      "model.layers.4.post_attention_layernorm",
+      "model.layers.4.self_attn.k_proj.bias",
+      "model.layers.4.self_attn.q_proj.bias",
+      "model.layers.4.self_attn.v_proj.bias",
+      "model.layers.4.mlp.shared_expert_gate",
+      "model.layers.5.mlp.shared_expert_gate",
+      "model.layers.5.input_layernorm",
+      "model.layers.5.mlp.gate",
+      "model.layers.5.post_attention_layernorm",
+      "model.layers.5.self_attn.k_proj.bias",
+      "model.layers.5.self_attn.q_proj.bias",
+      "model.layers.5.self_attn.v_proj.bias",
+      "model.layers.6.input_layernorm",
+      "model.layers.6.mlp.gate",
+      "model.layers.6.mlp.shared_expert_gate",
+      "model.layers.6.post_attention_layernorm",
+      "model.layers.6.self_attn.k_proj.bias",
+      "model.layers.6.self_attn.q_proj.bias",
+      "model.layers.6.self_attn.v_proj.bias",
+      "model.layers.7.input_layernorm",
+      "model.layers.7.mlp.gate",
+      "model.layers.7.post_attention_layernorm",
+      "model.layers.7.self_attn.k_proj.bias",
+      "model.layers.7.self_attn.q_proj.bias",
+      "model.layers.7.self_attn.v_proj.bias",
+      "model.layers.7.mlp.shared_expert_gate",
+      "model.layers.8.input_layernorm",
+      "model.layers.8.mlp.gate",
+      "model.layers.8.post_attention_layernorm",
+      "model.layers.8.self_attn.k_proj.bias",
+      "model.layers.8.self_attn.q_proj.bias",
+      "model.layers.8.self_attn.v_proj.bias",
+      "model.layers.8.mlp.shared_expert_gate",
+      "model.layers.9.input_layernorm",
+      "model.layers.9.mlp.gate",
+      "model.layers.9.mlp.shared_expert_gate",
+      "model.layers.9.post_attention_layernorm",
+      "model.layers.9.self_attn.k_proj.bias",
+      "model.layers.9.self_attn.q_proj.bias",
+      "model.layers.9.self_attn.v_proj.bias",
+      "model.layers.10.input_layernorm",
+      "model.layers.10.mlp.gate",
+      "model.layers.10.post_attention_layernorm",
+      "model.layers.10.self_attn.k_proj.bias",
+      "model.layers.10.self_attn.q_proj.bias",
+      "model.layers.10.self_attn.v_proj.bias",
+      "model.layers.10.mlp.shared_expert_gate",
+      "model.layers.11.mlp.shared_expert_gate",
+      "model.layers.11.input_layernorm",
+      "model.layers.11.mlp.gate",
+      "model.layers.11.post_attention_layernorm",
+      "model.layers.11.self_attn.k_proj.bias",
+      "model.layers.11.self_attn.q_proj.bias",
+      "model.layers.11.self_attn.v_proj.bias",
+      "model.layers.12.input_layernorm",
+      "model.layers.12.mlp.gate",
+      "model.layers.12.mlp.shared_expert_gate",
+      "model.layers.12.post_attention_layernorm",
+      "model.layers.12.self_attn.k_proj.bias",
+      "model.layers.12.self_attn.q_proj.bias",
+      "model.layers.12.self_attn.v_proj.bias",
+      "model.layers.13.mlp.shared_expert_gate",
+      "model.layers.13.input_layernorm",
+      "model.layers.13.mlp.gate",
+      "model.layers.13.post_attention_layernorm",
+      "model.layers.13.self_attn.k_proj.bias",
+      "model.layers.13.self_attn.q_proj.bias",
+      "model.layers.13.self_attn.v_proj.bias",
+      "model.layers.14.input_layernorm",
+      "model.layers.14.mlp.gate",
+      "model.layers.14.post_attention_layernorm",
+      "model.layers.14.self_attn.k_proj.bias",
+      "model.layers.14.self_attn.q_proj.bias",
+      "model.layers.14.self_attn.v_proj.bias",
+      "model.layers.14.mlp.shared_expert_gate",
+      "model.layers.15.input_layernorm",
+      "model.layers.15.mlp.gate",
+      "model.layers.15.mlp.shared_expert_gate",
+      "model.layers.15.post_attention_layernorm",
+      "model.layers.15.self_attn.k_proj.bias",
+      "model.layers.15.self_attn.q_proj.bias",
+      "model.layers.15.self_attn.v_proj.bias",
+      "model.layers.16.mlp.shared_expert_gate",
+      "model.layers.16.input_layernorm",
+      "model.layers.16.mlp.gate",
+      "model.layers.16.post_attention_layernorm",
+      "model.layers.16.self_attn.k_proj.bias",
+      "model.layers.16.self_attn.q_proj.bias",
+      "model.layers.16.self_attn.v_proj.bias",
+      "model.layers.17.mlp.shared_expert_gate",
+      "model.layers.17.input_layernorm",
+      "model.layers.17.mlp.gate",
+      "model.layers.17.post_attention_layernorm",
+      "model.layers.17.self_attn.k_proj.bias",
+      "model.layers.17.self_attn.q_proj.bias",
+      "model.layers.17.self_attn.v_proj.bias",
+      "model.layers.18.input_layernorm",
+      "model.layers.18.mlp.gate",
+      "model.layers.18.mlp.shared_expert_gate",
+      "model.layers.18.post_attention_layernorm",
+      "model.layers.18.self_attn.k_proj.bias",
+      "model.layers.18.self_attn.q_proj.bias",
+      "model.layers.18.self_attn.v_proj.bias",
+      "model.layers.19.mlp.shared_expert_gate",
+      "model.layers.19.input_layernorm",
+      "model.layers.19.mlp.gate",
+      "model.layers.19.post_attention_layernorm",
+      "model.layers.19.self_attn.k_proj.bias",
+      "model.layers.19.self_attn.q_proj.bias",
+      "model.layers.19.self_attn.v_proj.bias",
+      "model.layers.20.input_layernorm",
+      "model.layers.20.mlp.gate",
+      "model.layers.20.post_attention_layernorm",
+      "model.layers.20.self_attn.k_proj.bias",
+      "model.layers.20.self_attn.q_proj.bias",
+      "model.layers.20.self_attn.v_proj.bias",
+      "model.layers.20.mlp.shared_expert_gate",
+      "model.layers.21.input_layernorm",
+      "model.layers.21.mlp.gate",
+      "model.layers.21.mlp.shared_expert_gate",
+      "model.layers.21.post_attention_layernorm",
+      "model.layers.21.self_attn.k_proj.bias",
+      "model.layers.21.self_attn.q_proj.bias",
+      "model.layers.21.self_attn.v_proj.bias",
+      "model.layers.22.mlp.shared_expert_gate",
+      "model.layers.22.input_layernorm",
+      "model.layers.22.mlp.gate",
+      "model.layers.22.post_attention_layernorm",
+      "model.layers.22.self_attn.k_proj.bias",
+      "model.layers.22.self_attn.q_proj.bias",
+      "model.layers.22.self_attn.v_proj.bias",
+      "model.layers.23.input_layernorm",
+      "model.layers.23.mlp.gate",
+      "model.layers.23.mlp.shared_expert_gate",
+      "model.layers.23.post_attention_layernorm",
+      "model.layers.23.self_attn.k_proj.bias",
+      "model.layers.23.self_attn.q_proj.bias",
+      "model.layers.23.self_attn.v_proj.bias",
+      "model.layers.24.input_layernorm",
+      "model.layers.24.mlp.gate",
+      "model.layers.24.post_attention_layernorm",
+      "model.layers.24.self_attn.k_proj.bias",
+      "model.layers.24.self_attn.q_proj.bias",
+      "model.layers.24.self_attn.v_proj.bias",
+      "model.layers.24.mlp.shared_expert_gate",
+      "model.layers.25.mlp.shared_expert_gate",
+      "model.layers.25.input_layernorm",
+      "model.layers.25.mlp.gate",
+      "model.layers.25.post_attention_layernorm",
+      "model.layers.25.self_attn.k_proj.bias",
+      "model.layers.25.self_attn.q_proj.bias",
+      "model.layers.25.self_attn.v_proj.bias",
+      "model.layers.26.input_layernorm",
+      "model.layers.26.mlp.gate",
+      "model.layers.26.mlp.shared_expert_gate",
+      "model.layers.26.post_attention_layernorm",
+      "model.layers.26.self_attn.k_proj.bias",
+      "model.layers.26.self_attn.q_proj.bias",
+      "model.layers.26.self_attn.v_proj.bias",
+      "model.layers.27.input_layernorm",
+      "model.layers.27.mlp.gate",
+      "model.layers.27.post_attention_layernorm",
+      "model.layers.27.self_attn.k_proj.bias",
+      "model.layers.27.self_attn.q_proj.bias",
+      "model.layers.27.self_attn.v_proj.bias",
+      "model.layers.27.mlp.shared_expert_gate",
+      "model.layers.28.mlp.shared_expert_gate",
+      "model.layers.28.input_layernorm",
+      "model.layers.28.mlp.gate",
+      "model.layers.28.post_attention_layernorm",
+      "model.layers.28.self_attn.k_proj.bias",
+      "model.layers.28.self_attn.q_proj.bias",
+      "model.layers.28.self_attn.v_proj.bias",
+      "model.layers.29.input_layernorm",
+      "model.layers.29.mlp.gate",
+      "model.layers.29.mlp.shared_expert_gate",
+      "model.layers.29.post_attention_layernorm",
+      "model.layers.29.self_attn.k_proj.bias",
+      "model.layers.29.self_attn.q_proj.bias",
+      "model.layers.29.self_attn.v_proj.bias",
+      "model.layers.30.input_layernorm",
+      "model.layers.30.mlp.gate",
+      "model.layers.30.post_attention_layernorm",
+      "model.layers.30.self_attn.k_proj.bias",
+      "model.layers.30.self_attn.q_proj.bias",
+      "model.layers.30.self_attn.v_proj.bias",
+      "model.layers.30.mlp.shared_expert_gate",
+      "model.layers.31.input_layernorm",
+      "model.layers.31.mlp.gate",
+      "model.layers.31.post_attention_layernorm",
+      "model.layers.31.self_attn.k_proj.bias",
+      "model.layers.31.self_attn.q_proj.bias",
+      "model.layers.31.self_attn.v_proj.bias",
+      "model.layers.31.mlp.shared_expert_gate",
+      "model.layers.32.input_layernorm",
+      "model.layers.32.mlp.gate",
+      "model.layers.32.mlp.shared_expert_gate",
+      "model.layers.32.post_attention_layernorm",
+      "model.layers.32.self_attn.k_proj.bias",
+      "model.layers.32.self_attn.q_proj.bias",
+      "model.layers.32.self_attn.v_proj.bias",
+      "model.layers.33.input_layernorm",
+      "model.layers.33.mlp.gate",
+      "model.layers.33.mlp.shared_expert_gate",
+      "model.layers.33.post_attention_layernorm",
+      "model.layers.33.self_attn.k_proj.bias",
+      "model.layers.33.self_attn.q_proj.bias",
+      "model.layers.33.self_attn.v_proj.bias",
+      "model.layers.34.input_layernorm",
+      "model.layers.34.mlp.gate",
+      "model.layers.34.mlp.shared_expert_gate",
+      "model.layers.34.post_attention_layernorm",
+      "model.layers.34.self_attn.k_proj.bias",
+      "model.layers.34.self_attn.q_proj.bias",
+      "model.layers.34.self_attn.v_proj.bias",
+      "model.layers.35.input_layernorm",
+      "model.layers.35.mlp.gate",
+      "model.layers.35.mlp.shared_expert_gate",
+      "model.layers.35.post_attention_layernorm",
+      "model.layers.35.self_attn.k_proj.bias",
+      "model.layers.35.self_attn.q_proj.bias",
+      "model.layers.35.self_attn.v_proj.bias",
+      "model.layers.36.input_layernorm",
+      "model.layers.36.mlp.gate",
+      "model.layers.36.mlp.shared_expert_gate",
+      "model.layers.36.post_attention_layernorm",
+      "model.layers.36.self_attn.k_proj.bias",
+      "model.layers.36.self_attn.q_proj.bias",
+      "model.layers.36.self_attn.v_proj.bias",
+      "model.layers.37.input_layernorm",
+      "model.layers.37.mlp.gate",
+      "model.layers.37.mlp.shared_expert_gate",
+      "model.layers.37.post_attention_layernorm",
+      "model.layers.37.self_attn.k_proj.bias",
+      "model.layers.37.self_attn.q_proj.bias",
+      "model.layers.37.self_attn.v_proj.bias",
+      "model.layers.38.input_layernorm",
+      "model.layers.38.mlp.gate",
+      "model.layers.38.mlp.shared_expert_gate",
+      "model.layers.38.post_attention_layernorm",
+      "model.layers.38.self_attn.k_proj.bias",
+      "model.layers.38.self_attn.q_proj.bias",
+      "model.layers.38.self_attn.v_proj.bias",
+      "model.layers.39.input_layernorm",
+      "model.layers.39.mlp.gate",
+      "model.layers.39.mlp.shared_expert_gate",
+      "model.layers.39.post_attention_layernorm",
+      "model.layers.39.self_attn.k_proj.bias",
+      "model.layers.39.self_attn.q_proj.bias",
+      "model.layers.39.self_attn.v_proj.bias",
+      "model.layers.40.input_layernorm",
+      "model.layers.40.mlp.gate",
+      "model.layers.40.mlp.shared_expert_gate",
+      "model.layers.40.post_attention_layernorm",
+      "model.layers.40.self_attn.k_proj.bias",
+      "model.layers.40.self_attn.q_proj.bias",
+      "model.layers.40.self_attn.v_proj.bias",
+      "model.layers.41.input_layernorm",
+      "model.layers.41.mlp.gate",
+      "model.layers.41.mlp.shared_expert_gate",
+      "model.layers.41.post_attention_layernorm",
+      "model.layers.41.self_attn.k_proj.bias",
+      "model.layers.41.self_attn.q_proj.bias",
+      "model.layers.41.self_attn.v_proj.bias",
+      "model.layers.42.input_layernorm",
+      "model.layers.42.mlp.gate",
+      "model.layers.42.mlp.shared_expert_gate",
+      "model.layers.42.post_attention_layernorm",
+      "model.layers.42.self_attn.k_proj.bias",
+      "model.layers.42.self_attn.q_proj.bias",
+      "model.layers.42.self_attn.v_proj.bias",
+      "model.layers.43.input_layernorm",
+      "model.layers.43.mlp.gate",
+      "model.layers.43.mlp.shared_expert_gate",
+      "model.layers.43.post_attention_layernorm",
+      "model.layers.43.self_attn.k_proj.bias",
+      "model.layers.43.self_attn.q_proj.bias",
+      "model.layers.43.self_attn.v_proj.bias",
+      "model.layers.44.input_layernorm",
+      "model.layers.44.mlp.gate",
+      "model.layers.44.mlp.shared_expert_gate",
+      "model.layers.44.post_attention_layernorm",
+      "model.layers.44.self_attn.k_proj.bias",
+      "model.layers.44.self_attn.q_proj.bias",
+      "model.layers.44.self_attn.v_proj.bias",
+      "model.layers.45.input_layernorm",
+      "model.layers.45.mlp.gate",
+      "model.layers.45.mlp.shared_expert_gate",
+      "model.layers.45.post_attention_layernorm",
+      "model.layers.45.self_attn.k_proj.bias",
+      "model.layers.45.self_attn.q_proj.bias",
+      "model.layers.45.self_attn.v_proj.bias",
+      "model.layers.46.input_layernorm",
+      "model.layers.46.mlp.gate",
+      "model.layers.46.mlp.shared_expert_gate",
+      "model.layers.46.post_attention_layernorm",
+      "model.layers.46.self_attn.k_proj.bias",
+      "model.layers.46.self_attn.q_proj.bias",
+      "model.layers.46.self_attn.v_proj.bias",
+      "model.layers.47.input_layernorm",
+      "model.layers.47.mlp.gate",
+      "model.layers.47.mlp.shared_expert_gate",
+      "model.layers.47.post_attention_layernorm",
+      "model.layers.47.self_attn.k_proj.bias",
+      "model.layers.47.self_attn.q_proj.bias",
+      "model.layers.47.self_attn.v_proj.bias",
+      "lm_head",
+      "model.layers.0.input_layernorm",
+      "model.layers.0.mlp.gate",
+      "model.layers.0.mlp.shared_expert_gate",
+      "model.layers.0.post_attention_layernorm",
+      "model.layers.0.self_attn.k_proj.bias",
+      "model.layers.0.self_attn.q_proj.bias",
+      "model.layers.0.self_attn.v_proj.bias",
+      "model.layers.1.input_layernorm",
+      "model.layers.1.mlp.gate",
+      "model.layers.1.post_attention_layernorm",
+      "model.layers.1.self_attn.k_proj.bias",
+      "model.layers.1.self_attn.q_proj.bias",
+      "model.layers.1.self_attn.v_proj.bias",
+      "model.layers.1.mlp.shared_expert_gate",
+      "model.layers.2.mlp.shared_expert_gate",
+      "model.layers.2.input_layernorm",
+      "model.layers.2.mlp.gate",
+      "model.layers.2.post_attention_layernorm",
+      "model.layers.2.self_attn.k_proj.bias",
+      "model.layers.2.self_attn.q_proj.bias",
+      "model.layers.2.self_attn.v_proj.bias",
+      "model.layers.3.input_layernorm",
+      "model.layers.3.mlp.gate",
+      "model.layers.3.mlp.shared_expert_gate",
+      "model.layers.3.post_attention_layernorm",
+      "model.layers.3.self_attn.k_proj.bias",
+      "model.layers.3.self_attn.q_proj.bias",
+      "model.layers.3.self_attn.v_proj.bias",
+      "model.layers.4.input_layernorm",
+      "model.layers.4.mlp.gate",
+      "model.layers.4.post_attention_layernorm",
+      "model.layers.4.self_attn.k_proj.bias",
+      "model.layers.4.self_attn.q_proj.bias",
+      "model.layers.4.self_attn.v_proj.bias",
+      "model.layers.4.mlp.shared_expert_gate",
+      "model.layers.5.mlp.shared_expert_gate",
+      "model.layers.5.input_layernorm",
+      "model.layers.5.mlp.gate",
+      "model.layers.5.post_attention_layernorm",
+      "model.layers.5.self_attn.k_proj.bias",
+      "model.layers.5.self_attn.q_proj.bias",
+      "model.layers.5.self_attn.v_proj.bias",
+      "model.layers.6.input_layernorm",
+      "model.layers.6.mlp.gate",
+      "model.layers.6.mlp.shared_expert_gate",
+      "model.layers.6.post_attention_layernorm",
+      "model.layers.6.self_attn.k_proj.bias",
+      "model.layers.6.self_attn.q_proj.bias",
+      "model.layers.6.self_attn.v_proj.bias",
+      "model.layers.7.input_layernorm",
+      "model.layers.7.mlp.gate",
+      "model.layers.7.post_attention_layernorm",
+      "model.layers.7.self_attn.k_proj.bias",
+      "model.layers.7.self_attn.q_proj.bias",
+      "model.layers.7.self_attn.v_proj.bias",
+      "model.layers.7.mlp.shared_expert_gate",
+      "model.layers.8.input_layernorm",
+      "model.layers.8.mlp.gate",
+      "model.layers.8.post_attention_layernorm",
+      "model.layers.8.self_attn.k_proj.bias",
+      "model.layers.8.self_attn.q_proj.bias",
+      "model.layers.8.self_attn.v_proj.bias",
+      "model.layers.8.mlp.shared_expert_gate",
+      "model.layers.9.input_layernorm",
+      "model.layers.9.mlp.gate",
+      "model.layers.9.mlp.shared_expert_gate",
+      "model.layers.9.post_attention_layernorm",
+      "model.layers.9.self_attn.k_proj.bias",
+      "model.layers.9.self_attn.q_proj.bias",
+      "model.layers.9.self_attn.v_proj.bias",
+      "model.layers.10.input_layernorm",
+      "model.layers.10.mlp.gate",
+      "model.layers.10.post_attention_layernorm",
+      "model.layers.10.self_attn.k_proj.bias",
+      "model.layers.10.self_attn.q_proj.bias",
+      "model.layers.10.self_attn.v_proj.bias",
+      "model.layers.10.mlp.shared_expert_gate",
+      "model.layers.11.mlp.shared_expert_gate",
+      "model.layers.11.input_layernorm",
+      "model.layers.11.mlp.gate",
+      "model.layers.11.post_attention_layernorm",
+      "model.layers.11.self_attn.k_proj.bias",
+      "model.layers.11.self_attn.q_proj.bias",
+      "model.layers.11.self_attn.v_proj.bias",
+      "model.layers.12.input_layernorm",
+      "model.layers.12.mlp.gate",
+      "model.layers.12.mlp.shared_expert_gate",
+      "model.layers.12.post_attention_layernorm",
+      "model.layers.12.self_attn.k_proj.bias",
+      "model.layers.12.self_attn.q_proj.bias",
+      "model.layers.12.self_attn.v_proj.bias",
+      "model.layers.13.mlp.shared_expert_gate",
+      "model.layers.13.input_layernorm",
+      "model.layers.13.mlp.gate",
+      "model.layers.13.post_attention_layernorm",
+      "model.layers.13.self_attn.k_proj.bias",
+      "model.layers.13.self_attn.q_proj.bias",
+      "model.layers.13.self_attn.v_proj.bias",
+      "model.layers.14.input_layernorm",
+      "model.layers.14.mlp.gate",
+      "model.layers.14.post_attention_layernorm",
+      "model.layers.14.self_attn.k_proj.bias",
+      "model.layers.14.self_attn.q_proj.bias",
+      "model.layers.14.self_attn.v_proj.bias",
+      "model.layers.14.mlp.shared_expert_gate",
+      "model.layers.15.input_layernorm",
+      "model.layers.15.mlp.gate",
+      "model.layers.15.mlp.shared_expert_gate",
+      "model.layers.15.post_attention_layernorm",
+      "model.layers.15.self_attn.k_proj.bias",
+      "model.layers.15.self_attn.q_proj.bias",
+      "model.layers.15.self_attn.v_proj.bias",
+      "model.layers.16.mlp.shared_expert_gate",
+      "model.layers.16.input_layernorm",
+      "model.layers.16.mlp.gate",
+      "model.layers.16.post_attention_layernorm",
+      "model.layers.16.self_attn.k_proj.bias",
+      "model.layers.16.self_attn.q_proj.bias",
+      "model.layers.16.self_attn.v_proj.bias",
+      "model.layers.17.mlp.shared_expert_gate",
+      "model.layers.17.input_layernorm",
+      "model.layers.17.mlp.gate",
+      "model.layers.17.post_attention_layernorm",
+      "model.layers.17.self_attn.k_proj.bias",
+      "model.layers.17.self_attn.q_proj.bias",
+      "model.layers.17.self_attn.v_proj.bias",
+      "model.layers.18.input_layernorm",
+      "model.layers.18.mlp.gate",
+      "model.layers.18.mlp.shared_expert_gate",
+      "model.layers.18.post_attention_layernorm",
+      "model.layers.18.self_attn.k_proj.bias",
+      "model.layers.18.self_attn.q_proj.bias",
+      "model.layers.18.self_attn.v_proj.bias",
+      "model.layers.19.mlp.shared_expert_gate",
+      "model.layers.19.input_layernorm",
+      "model.layers.19.mlp.gate",
+      "model.layers.19.post_attention_layernorm",
+      "model.layers.19.self_attn.k_proj.bias",
+      "model.layers.19.self_attn.q_proj.bias",
+      "model.layers.19.self_attn.v_proj.bias",
+      "model.layers.20.input_layernorm",
+      "model.layers.20.mlp.gate",
+      "model.layers.20.post_attention_layernorm",
+      "model.layers.20.self_attn.k_proj.bias",
+      "model.layers.20.self_attn.q_proj.bias",
+      "model.layers.20.self_attn.v_proj.bias",
+      "model.layers.20.mlp.shared_expert_gate",
+      "model.layers.21.input_layernorm",
+      "model.layers.21.mlp.gate",
+      "model.layers.21.mlp.shared_expert_gate",
+      "model.layers.21.post_attention_layernorm",
+      "model.layers.21.self_attn.k_proj.bias",
+      "model.layers.21.self_attn.q_proj.bias",
+      "model.layers.21.self_attn.v_proj.bias",
+      "model.layers.22.mlp.shared_expert_gate",
+      "model.layers.22.input_layernorm",
+      "model.layers.22.mlp.gate",
+      "model.layers.22.post_attention_layernorm",
+      "model.layers.22.self_attn.k_proj.bias",
+      "model.layers.22.self_attn.q_proj.bias",
+      "model.layers.22.self_attn.v_proj.bias",
+      "model.layers.23.input_layernorm",
+      "model.layers.23.mlp.gate",
+      "model.layers.23.mlp.shared_expert_gate",
+      "model.layers.23.post_attention_layernorm",
+      "model.layers.23.self_attn.k_proj.bias",
+      "model.layers.23.self_attn.q_proj.bias",
+      "model.layers.23.self_attn.v_proj.bias",
+      "model.layers.24.input_layernorm",
+      "model.layers.24.mlp.gate",
+      "model.layers.24.post_attention_layernorm",
+      "model.layers.24.self_attn.k_proj.bias",
+      "model.layers.24.self_attn.q_proj.bias",
+      "model.layers.24.self_attn.v_proj.bias",
+      "model.layers.24.mlp.shared_expert_gate",
+      "model.layers.25.mlp.shared_expert_gate",
+      "model.layers.25.input_layernorm",
+      "model.layers.25.mlp.gate",
+      "model.layers.25.post_attention_layernorm",
+      "model.layers.25.self_attn.k_proj.bias",
+      "model.layers.25.self_attn.q_proj.bias",
+      "model.layers.25.self_attn.v_proj.bias",
+      "model.layers.26.input_layernorm",
+      "model.layers.26.mlp.gate",
+      "model.layers.26.mlp.shared_expert_gate",
+      "model.layers.26.post_attention_layernorm",
+      "model.layers.26.self_attn.k_proj.bias",
+      "model.layers.26.self_attn.q_proj.bias",
+      "model.layers.26.self_attn.v_proj.bias",
+      "model.layers.27.input_layernorm",
+      "model.layers.27.mlp.gate",
+      "model.layers.27.post_attention_layernorm",
+      "model.layers.27.self_attn.k_proj.bias",
+      "model.layers.27.self_attn.q_proj.bias",
+      "model.layers.27.self_attn.v_proj.bias",
+      "model.layers.27.mlp.shared_expert_gate",
+      "model.layers.28.mlp.shared_expert_gate",
+      "model.layers.28.input_layernorm",
+      "model.layers.28.mlp.gate",
+      "model.layers.28.post_attention_layernorm",
+      "model.layers.28.self_attn.k_proj.bias",
+      "model.layers.28.self_attn.q_proj.bias",
+      "model.layers.28.self_attn.v_proj.bias",
+      "model.layers.29.input_layernorm",
+      "model.layers.29.mlp.gate",
+      "model.layers.29.mlp.shared_expert_gate",
+      "model.layers.29.post_attention_layernorm",
+      "model.layers.29.self_attn.k_proj.bias",
+      "model.layers.29.self_attn.q_proj.bias",
+      "model.layers.29.self_attn.v_proj.bias",
+      "model.layers.30.input_layernorm",
+      "model.layers.30.mlp.gate",
+      "model.layers.30.post_attention_layernorm",
+      "model.layers.30.self_attn.k_proj.bias",
+      "model.layers.30.self_attn.q_proj.bias",
+      "model.layers.30.self_attn.v_proj.bias",
+      "model.layers.30.mlp.shared_expert_gate",
+      "model.layers.31.input_layernorm",
+      "model.layers.31.mlp.gate",
+      "model.layers.31.post_attention_layernorm",
+      "model.layers.31.self_attn.k_proj.bias",
+      "model.layers.31.self_attn.q_proj.bias",
+      "model.layers.31.self_attn.v_proj.bias",
+      "model.layers.31.mlp.shared_expert_gate",
+      "model.layers.32.input_layernorm",
+      "model.layers.32.mlp.gate",
+      "model.layers.32.mlp.shared_expert_gate",
+      "model.layers.32.post_attention_layernorm",
+      "model.layers.32.self_attn.k_proj.bias",
+      "model.layers.32.self_attn.q_proj.bias",
+      "model.layers.32.self_attn.v_proj.bias",
+      "model.layers.33.input_layernorm",
+      "model.layers.33.mlp.gate",
+      "model.layers.33.mlp.shared_expert_gate",
+      "model.layers.33.post_attention_layernorm",
+      "model.layers.33.self_attn.k_proj.bias",
+      "model.layers.33.self_attn.q_proj.bias",
+      "model.layers.33.self_attn.v_proj.bias",
+      "model.layers.34.input_layernorm",
+      "model.layers.34.mlp.gate",
+      "model.layers.34.mlp.shared_expert_gate",
+      "model.layers.34.post_attention_layernorm",
+      "model.layers.34.self_attn.k_proj.bias",
+      "model.layers.34.self_attn.q_proj.bias",
+      "model.layers.34.self_attn.v_proj.bias",
+      "model.layers.35.input_layernorm",
+      "model.layers.35.mlp.gate",
+      "model.layers.35.mlp.shared_expert_gate",
+      "model.layers.35.post_attention_layernorm",
+      "model.layers.35.self_attn.k_proj.bias",
+      "model.layers.35.self_attn.q_proj.bias",
+      "model.layers.35.self_attn.v_proj.bias",
+      "model.layers.36.input_layernorm",
+      "model.layers.36.mlp.gate",
+      "model.layers.36.mlp.shared_expert_gate",
+      "model.layers.36.post_attention_layernorm",
+      "model.layers.36.self_attn.k_proj.bias",
+      "model.layers.36.self_attn.q_proj.bias",
+      "model.layers.36.self_attn.v_proj.bias",
+      "model.layers.37.input_layernorm",
+      "model.layers.37.mlp.gate",
+      "model.layers.37.mlp.shared_expert_gate",
+      "model.layers.37.post_attention_layernorm",
+      "model.layers.37.self_attn.k_proj.bias",
+      "model.layers.37.self_attn.q_proj.bias",
+      "model.layers.37.self_attn.v_proj.bias",
+      "model.layers.38.input_layernorm",
+      "model.layers.38.mlp.gate",
+      "model.layers.38.mlp.shared_expert_gate",
+      "model.layers.38.post_attention_layernorm",
+      "model.layers.38.self_attn.k_proj.bias",
+      "model.layers.38.self_attn.q_proj.bias",
+      "model.layers.38.self_attn.v_proj.bias",
+      "model.layers.39.input_layernorm",
+      "model.layers.39.mlp.gate",
+      "model.layers.39.mlp.shared_expert_gate",
+      "model.layers.39.post_attention_layernorm",
+      "model.layers.39.self_attn.k_proj.bias",
+      "model.layers.39.self_attn.q_proj.bias",
+      "model.layers.39.self_attn.v_proj.bias",
+      "model.layers.40.input_layernorm",
+      "model.layers.40.mlp.gate",
+      "model.layers.40.mlp.shared_expert_gate",
+      "model.layers.40.post_attention_layernorm",
+      "model.layers.40.self_attn.k_proj.bias",
+      "model.layers.40.self_attn.q_proj.bias",
+      "model.layers.40.self_attn.v_proj.bias",
+      "model.layers.41.input_layernorm",
+      "model.layers.41.mlp.gate",
+      "model.layers.41.mlp.shared_expert_gate",
+      "model.layers.41.post_attention_layernorm",
+      "model.layers.41.self_attn.k_proj.bias",
+      "model.layers.41.self_attn.q_proj.bias",
+      "model.layers.41.self_attn.v_proj.bias",
+      "model.layers.42.input_layernorm",
+      "model.layers.42.mlp.gate",
+      "model.layers.42.mlp.shared_expert_gate",
+      "model.layers.42.post_attention_layernorm",
+      "model.layers.42.self_attn.k_proj.bias",
+      "model.layers.42.self_attn.q_proj.bias",
+      "model.layers.42.self_attn.v_proj.bias",
+      "model.layers.43.input_layernorm",
+      "model.layers.43.mlp.gate",
+      "model.layers.43.mlp.shared_expert_gate",
+      "model.layers.43.post_attention_layernorm",
+      "model.layers.43.self_attn.k_proj.bias",
+      "model.layers.43.self_attn.q_proj.bias",
+      "model.layers.43.self_attn.v_proj.bias",
+      "model.layers.44.input_layernorm",
+      "model.layers.44.mlp.gate",
+      "model.layers.44.mlp.shared_expert_gate",
+      "model.layers.44.post_attention_layernorm",
+      "model.layers.44.self_attn.k_proj.bias",
+      "model.layers.44.self_attn.q_proj.bias",
+      "model.layers.44.self_attn.v_proj.bias",
+      "model.layers.45.input_layernorm",
+      "model.layers.45.mlp.gate",
+      "model.layers.45.mlp.shared_expert_gate",
+      "model.layers.45.post_attention_layernorm",
+      "model.layers.45.self_attn.k_proj.bias",
+      "model.layers.45.self_attn.q_proj.bias",
+      "model.layers.45.self_attn.v_proj.bias",
+      "model.layers.46.input_layernorm",
+      "model.layers.46.mlp.gate",
+      "model.layers.46.mlp.shared_expert_gate",
+      "model.layers.46.post_attention_layernorm",
+      "model.layers.46.self_attn.k_proj.bias",
+      "model.layers.46.self_attn.q_proj.bias",
+      "model.layers.46.self_attn.v_proj.bias",
+      "model.layers.47.input_layernorm",
+      "model.layers.47.mlp.gate",
+      "model.layers.47.mlp.shared_expert_gate",
+      "model.layers.47.post_attention_layernorm",
+      "model.layers.47.self_attn.k_proj.bias",
+      "model.layers.47.self_attn.q_proj.bias",
+      "model.layers.47.self_attn.v_proj.bias"
+    ],
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_grouped_gemm": false,
+  "use_qk_norm": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-generation"}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 151645,
+  "pad_token_id": 151643,
+  "transformers_version": "4.51.0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8491994563a8ef470fe940838d7346d9d3d1bab94c20d502ea296cc911889bd
+size 5000178568

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c35060a9398b98a3dc4f6aca05a8d0e3e9a895a5c0b63087bc3aeee61c30c0ba
+size 4993354584

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555993d80ccf12dfc63a6c19f6b54f8252e48819f07a0b52c29f66959415c379
+size 4993357688

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714ec1cab66a49faad208ad96891a0d3214cbfc546c6de2dc62569f4ad5945d0
+size 4993357688

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d9da7fd143c96c53f32aad7cfad873c3b4947cd204fa20d301e83f53161afe
+size 4993357688

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74d23e6c0978f437962cd074e9a708b447451bfc398b1d27f2f70f6558fc934e
+size 4993357688

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd3273ac4b27382172c7fb80632da3b08f8da83fd2826af44698e15247d088f
+size 2482523864

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- '' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n  {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" and not message.tool_calls %}\n        {%- set content = message.content %}\n        {%- if not loop.last %}\n            {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n        {%- endif %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- if not loop.last %}\n            {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n        {%- endif %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}