https://github.com/FlagAI-Open/FlagAI/tree/master/examples/Aquila
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained('qhduan/aquila-7b')
model = AutoModelForCausalLM.from_pretrained('qhduan/aquila-7b', trust_remote_code=True)
model = model.eval().half().cuda()
prompt = '北京在哪儿?'
with torch.no_grad():
ret = model.generate(
**tokenizer(prompt, return_tensors='pt').to('cuda'),
do_sample=False,
max_new_tokens=200,
use_cache=True
)
# 北京在哪儿? 北京是中国的首都,是中华人民共和国的首都,是全国政治、经济、文化、交通中心,是世界著名古都和现代化国际城市
print(tokenizer.decode(ret[0]))
Aquila-7B和Aquila-33B开源模型使用 智源Aquila系列模型许可协议, 原始代码基于Apache Licence 2.0。
- Downloads last month
- 21
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.