初始化项目，由ModelHub XC社区提供模型

Model: liyinghong/BioQwen-0.5B
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,78 @@
+---
+license: mit
+datasets:
+- yueqingyou/BioQwen
+language:
+- en
+- zh
+tags:
+- BioQwen
+- 0.5B
+- Biomedical
+- Multi-Tasks
+---
+
+# BioQwen: A Small-Parameter, High-Performance Bilingual Model for Biomedical Multi-Tasks
+
+For model inference, please refer to the following example code:
+
+```python
+import torch
+import transformers
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+transformers.logging.set_verbosity_error()
+max_length = 512
+model_path = 'yueqingyou/BioQwen-0.5B'
+tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True)
+model = AutoModelForCausalLM.from_pretrained(model_path, device_map='auto', torch_dtype=torch.bfloat16, attn_implementation='flash_attention_2').eval()
+
+def predict(prompt):
+    zh_system = "你是千问生物智能助手，一个专注于生物领域的先进人工智能。"
+    en_system = "You are BioQwen, an advanced AI specializing in the field of biology."
+    
+    english_count, chinese_count = 0, 0
+    for char in prompt:
+        if '\u4e00' <= char <= '\u9fff':
+            chinese_count += 1
+        elif 'a' <= char.lower() <= 'z':
+            english_count += 1
+    lang = 'zh' if chinese_count > english_count else 'en'
+    
+    messages = [
+        {"role": "system", "content": zh_system if lang == 'zh' else en_system},
+        {"role": "user", "content": prompt}
+    ]
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+
+    model_inputs = tokenizer([text], return_tensors="pt").to('cuda')
+
+    with torch.no_grad():
+        generated_ids = model.generate(
+            model_inputs.input_ids,
+            max_new_tokens=max_length,
+            eos_token_id=tokenizer.eos_token_id,
+            pad_token_id=tokenizer.pad_token_id,
+            do_sample=True,
+            top_p = 0.9,
+            temperature = 0.3,
+            repetition_penalty = 1.1
+        )
+
+    generated_ids = [
+        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+    ]
+    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    
+    return response.strip()
+
+prompt = 'I am suffering from irregular periods. I am currently taking medication Levothyroxine 50. My T3 is 0.87 ng/mL, T4 is 8.30 ug/dL, TSH is 2.43 uIU/mL. I am 34 years old, weigh 75 kg, and 5 feet tall. Please advice.'
+print(f'Question:\t{prompt}\n\nAnswer:\t{predict(prompt)}')
+
+```
+
+For more detailed information and code, please refer to [GitHub](https://github.com/yueqingyou/BioQwen).

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|padoftext|>": 151646
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "bio-qwen2-stage1-merged/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.40.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55bf78d3331503cca4cbc2934df41a3e1181878c70318294fa6260ac76233feb
+size 988097824

model.safetensors.index.json

@@ -0,0 +1,294 @@
+{
+  "weight_map": {
+    "model.embed_tokens.weight": "model.safetensors",
+    "model.layers.0.input_layernorm.weight": "model.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.1.input_layernorm.weight": "model.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.10.input_layernorm.weight": "model.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.11.input_layernorm.weight": "model.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.12.input_layernorm.weight": "model.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.13.input_layernorm.weight": "model.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.14.input_layernorm.weight": "model.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.15.input_layernorm.weight": "model.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.16.input_layernorm.weight": "model.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.17.input_layernorm.weight": "model.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.18.input_layernorm.weight": "model.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.19.input_layernorm.weight": "model.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.2.input_layernorm.weight": "model.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.20.input_layernorm.weight": "model.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.21.input_layernorm.weight": "model.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.22.input_layernorm.weight": "model.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.23.input_layernorm.weight": "model.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.3.input_layernorm.weight": "model.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.4.input_layernorm.weight": "model.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.5.input_layernorm.weight": "model.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.6.input_layernorm.weight": "model.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.7.input_layernorm.weight": "model.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.8.input_layernorm.weight": "model.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.9.input_layernorm.weight": "model.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+    "model.norm.weight": "model.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|padoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "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": "<|padoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|padoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}