README_zh.md

metadata

license: other

English 简体中文 |

悟道·天鹰（Aquila2）

我们开源了我们的 Aquila2 系列，现在包括基础语言模型 Aquila2-7B 和 Aquila2-34B ，对话模型 AquilaChat2-7B 和 AquilaChat2-34B，长文本对话模型AquilaChat2-7B-16k 和 AquilaChat2-34B-16k

悟道 · 天鹰 Aquila 模型的更多细节将在官方技术报告中呈现。请关注官方渠道更新。

对话模型性能

Quick Start AquilaChat-7B（Chat model）

1. Inference

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
device = torch.device("cuda")
model_info = "BAAI/AquilaChat2-7B"
tokenizer = AutoTokenizer.from_pretrained(model_info, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_info, trust_remote_code=True)
model.eval()
model.to(device)
text = "请给出10个要到北京旅游的理由。"
tokens = tokenizer.encode_plus(text)['input_ids'][:-1]
tokens = torch.tensor(tokens)[None,].to(device)
stop_tokens = ["###", "[UNK]", "</s>"]
with torch.no_grad():
    out = model.generate(tokens, do_sample=True, max_length=512, eos_token_id=100007, bad_words_ids=[[tokenizer.encode(token)[0] for token in stop_tokens]])[0]
    out = tokenizer.decode(out.cpu().numpy().tolist())
    print(out)

License

AquilaChat2-7B open-source model is licensed under BAAI Aquila Model Licence Agreement