README.md

metadata

title: chinese-alpaca-plus-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，得到的中文LLaMA-plus模型。

详情可参考：https://github.com/ymcui/Chinese-LLaMA-Alpaca/releases/tag/v3.0

使用方法参考

1. 安装模块包

pip install sentencepiece
pip install transformers>=4.28.0

2. 生成文本

import torch
import transformers
from transformers import LlamaTokenizer, LlamaForCausalLM


tokenizer = LlamaTokenizer.from_pretrained('minlik/chinese-llama-plus-7b-merged')
model = LlamaForCausalLM.from_pretrained('minlik/chinese-llama-plus-7b-merged').half().to('cuda')
model.eval()

text = '第一个登上月球的人是'
input_ids = tokenizer.encode(text, 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())