初始化项目，由ModelHub XC社区提供模型

Model: Vnhukvm/Doctor-Qwen2 Source: Original Platform
2026-10-20 07:17:16 +08:00
commit 4b3dfc1f52
12 changed files with 454784 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,119 @@
+## 模型介绍
+
+Doctor-Qwen2是一个为医疗健康对话场景而打造的领域大模型，该模型基于Qwen2-1.5B-Instruct进行微调得来，使用的数据集是[复旦大学数据智能与社会计算实验室](http://fudan-disc.com)开源的[DISC-Med-SFT](https://huggingface.co/datasets/Flmc/DISC-Med-SFT)数据集。
+
+## 模型推理范例
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("模型路径")
+model = AutoModelForCausalLM.from_pretrained("模型路径", device_map={"":0})
+
+prompt = "医生您好，我最近睡眠质量很差，晚上经常醒来，而且早上起来也疲惫不堪，我该如何才能改善睡眠质量？"
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+device = 'cuda'
+model_inputs = tokenizer([text], return_tensors="pt").to(device)
+
+generated_ids = model.generate( model_inputs.input_ids, max_new_tokens=512)
+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]
+print(response)
+```
+
+## 数据集预处理
+
+假设原数据集里包括许多一轮对话，每一段对话的格式如下：
+
+```
+{   
+    "instruction": "*********",
+    "input": "*********", 
+    "output": "*********"
+}
+```
+
+```python
+from datasets import Dataset
+import pandas as pd
+
+def process_func(example):
+    """
+    将数据集进行预处理
+    """
+    MAX_LENGTH = 384 
+    input_ids, attention_mask, labels = [], [], []
+    instruction = tokenizer(
+        f"<|im_start|>system\n你是一个医疗领域的专家，你会接收到病人的提问，请输出合适的答案<|im_end|>\n<|im_start|>user\n{example['input']}<|im_end|>\n<|im_start|>assistant\n",
+        add_special_tokens=False,
+    )
+    response = tokenizer(f"{example['output']}", add_special_tokens=False)
+    input_ids = instruction["input_ids"] + response["input_ids"] + [tokenizer.pad_token_id]
+    attention_mask = (
+        instruction["attention_mask"] + response["attention_mask"] + [1]
+    )
+    labels = [-100] * len(instruction["input_ids"]) + response["input_ids"] + [tokenizer.pad_token_id]
+    return {"input_ids": input_ids, "attention_mask": attention_mask, "labels": labels}  
+
+train_df = pd.read_json("原数据集路径", lines=True)
+train_ds = Dataset.from_pandas(train_df)
+train_dataset = train_ds.map(process_func, remove_columns=train_ds.column_names)
+```
+
+## 模型微调范例
+
+使用LoRA技术对模型进行微调，以满足特定任务需求。
+
+```python
+from trl import SFTTrainer
+from peft import LoraConfig, TaskType
+from transformers import AutoModelForCausalLM, TrainingArguments, DataCollatorForSeq2Seq, AutoTokenizer
+from datasets import load_from_disk
+
+train_dataset = load_from_disk("处理过的数据集路径")
+tokenizer = AutoTokenizer.from_pretrained("模型路径")
+model = AutoModelForCausalLM.from_pretrained("模型路径", device_map={"":0})
+
+lora_config = LoraConfig(
+    task_type=TaskType.CAUSAL_LM,
+    target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
+    inference_mode=False,  
+    r=8, 
+    lora_alpha=32, 
+    lora_dropout=0.1, 
+)
+
+args = TrainingArguments(
+    output_dir="自定义输出路径",
+    per_device_train_batch_size=5,
+    gradient_accumulation_steps=5,
+    logging_steps=10,
+    num_train_epochs=3,
+    save_steps=100,
+    learning_rate=1e-4,
+    save_on_each_node=True, 
+    gradient_checkpointing=True,
+    report_to="none",
+)
+
+trainer = SFTTrainer(
+    model=model,
+    args=args,
+    train_dataset=train_dataset,
+    data_collator=DataCollatorForSeq2Seq(tokenizer=tokenizer, padding=True),
+    peft_config=lora_config,
+)
+
+trainer.train()
+```
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "/mnt/workspace/.cache/modelscope/hub/qwen/Qwen2-1___5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"task":"text-generation"}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "top_p": 0.8,
+  "transformers_version": "4.41.2"
+}
--- a/merges.txt
+++ b/merges.txt
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db160ddc0fb3061822048f9aac04c84cfad719149231546787837172e88bcd9b
+size 1671198284
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,43 @@
+{
+  "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": "{% 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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/vocab.json
+++ b/vocab.json