58 lines
1.4 KiB
Markdown
58 lines
1.4 KiB
Markdown
---
|
||
title: chinese-alpaca-7b-merged
|
||
emoji: 📚
|
||
colorFrom: gray
|
||
colorTo: red
|
||
sdk: gradio
|
||
sdk_version: 3.23.0
|
||
app_file: app.py
|
||
pinned: false
|
||
---
|
||
|
||
加入中文词表并继续预训练中文Embedding，并在此基础上继续使用指令数据集finetuning，得到的中文LLaMA模型。
|
||
|
||
详情可参考：https://github.com/ymcui/Chinese-LLaMA-Alpaca
|
||
|
||
### 使用方法参考
|
||
1. 安装模块包
|
||
```bash
|
||
pip install sentencepiece
|
||
pip install transformers>=4.28.0
|
||
```
|
||
|
||
2. 生成文本
|
||
```python
|
||
import torch
|
||
import transformers
|
||
from transformers import LlamaTokenizer, LlamaForCausalLM
|
||
|
||
def generate_prompt(text):
|
||
return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
||
|
||
### Instruction:
|
||
{text}
|
||
|
||
### Response:"""
|
||
|
||
|
||
tokenizer = LlamaTokenizer.from_pretrained('minlik/chinese-alpaca-7b-merged')
|
||
model = LlamaForCausalLM.from_pretrained('minlik/chinese-alpaca-7b-merged').half().to('cuda')
|
||
model.eval()
|
||
|
||
text = '第一个登上月球的人是谁？'
|
||
prompt = generate_prompt(text)
|
||
input_ids = tokenizer.encode(prompt, return_tensors='pt').to('cuda')
|
||
|
||
|
||
with torch.no_grad():
|
||
output_ids = model.generate(
|
||
input_ids=input_ids,
|
||
max_new_tokens=128,
|
||
temperature=1,
|
||
top_k=40,
|
||
top_p=0.9,
|
||
repetition_penalty=1.15
|
||
).cuda()
|
||
output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
|
||
print(output.replace(prompt, '').strip())
|
||
``` |