110 lines
2.7 KiB
Markdown
110 lines
2.7 KiB
Markdown
|
---
|
|||
|
|
frameworks:
|
|||
|
|
- Pytorch
|
|||
|
|
license: Apache License 2.0
|
|||
|
|
tasks:
|
|||
|
|
- text-generation
|
|||
|
|
|
|||
|
|
#model-type:
|
|||
|
|
##如 gpt、phi、llama、chatglm、baichuan 等
|
|||
|
|
#- gpt
|
|||
|
|
|
|||
|
|
#domain:
|
|||
|
|
##如 nlp、cv、audio、multi-modal
|
|||
|
|
#- nlp
|
|||
|
|
|
|||
|
|
#language:
|
|||
|
|
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
|||
|
|
#- cn
|
|||
|
|
|
|||
|
|
#metrics:
|
|||
|
|
##如 CIDEr、Blue、ROUGE 等
|
|||
|
|
#- CIDEr
|
|||
|
|
|
|||
|
|
#tags:
|
|||
|
|
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
|||
|
|
#- pretrained
|
|||
|
|
|
|||
|
|
#tools:
|
|||
|
|
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
|||
|
|
#- vllm
|
|||
|
|
---
|
|||
|
|
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
|
|||
|
|
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
|
|||
|
|
|
|||
|
|
SDK下载
|
|||
|
|
```bash
|
|||
|
|
#安装ModelScope
|
|||
|
|
pip install modelscope
|
|||
|
|
```
|
|||
|
|
```python
|
|||
|
|
#SDK模型下载
|
|||
|
|
from modelscope import snapshot_download
|
|||
|
|
model_dir = snapshot_download('bruce870101/qwen2.5_7B_traditional_chinese_medicine')
|
|||
|
|
|
|||
|
|
```
|
|||
|
|
Git下载
|
|||
|
|
```
|
|||
|
|
#Git模型下载
|
|||
|
|
git clone https://www.modelscope.cn/bruce870101/qwen2.5_7B_traditional_chinese_medicine.git
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
本地加载模型的试用案例
|
|||
|
|
```
|
|||
|
|
from transformers import AutoTokenizer
|
|||
|
|
from transformers.models.qwen2 import Qwen2ForCausalLM
|
|||
|
|
import torch
|
|||
|
|
|
|||
|
|
model_path = 大模型的本地绝对路径
|
|||
|
|
|
|||
|
|
# 加载分词器和模型
|
|||
|
|
tokenizer = AutoTokenizer.from_pretrained(
|
|||
|
|
model_path,
|
|||
|
|
trust_remote_code=True,
|
|||
|
|
local_files_only=True
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
model = Qwen2ForCausalLM.from_pretrained(
|
|||
|
|
model_path,
|
|||
|
|
trust_remote_code=True,
|
|||
|
|
torch_dtype=torch.float16,
|
|||
|
|
device_map="auto",
|
|||
|
|
local_files_only=True
|
|||
|
|
).eval()
|
|||
|
|
|
|||
|
|
# 使用 Qwen2.5 的正确生成方式
|
|||
|
|
prompt = "你好，请解析一下中医所说的气，是指什么？"
|
|||
|
|
|
|||
|
|
# 使用聊天模板构建输入
|
|||
|
|
messages = [
|
|||
|
|
{"role": "system", "content": "你是一个知识渊博的中医医疗助手"},
|
|||
|
|
{"role": "user", "content": prompt}
|
|||
|
|
]
|
|||
|
|
|
|||
|
|
# 应用聊天模板
|
|||
|
|
text = tokenizer.apply_chat_template(
|
|||
|
|
messages,
|
|||
|
|
tokenize=False,
|
|||
|
|
add_generation_prompt=True
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
# 编码输入
|
|||
|
|
inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
|||
|
|
|
|||
|
|
# 生成回复
|
|||
|
|
outputs = model.generate(
|
|||
|
|
**inputs,
|
|||
|
|
max_new_tokens=512,
|
|||
|
|
pad_token_id=tokenizer.eos_token_id,
|
|||
|
|
eos_token_id=tokenizer.eos_token_id,
|
|||
|
|
do_sample=True,
|
|||
|
|
temperature=0.7,
|
|||
|
|
top_p=0.9
|
|||
|
|
)
|
|||
|
|
response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
|
|||
|
|
print(response)
|
|||
|
|
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
|
|||
|
|
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
|