--- license: other ---  <h4 align="center"> <p> <b>English</b> | <a href="https://huggingface.co/BAAI/AquilaChat2-7B/blob/main/README_zh.md">简体中文</a> </p> </h4> We opensource our **Aquila2** series, now including **Aquila2**, the base language models, namely **Aquila2-7B**, **Aquila2-34B** and **Aquila2-70B** , as well as **AquilaChat2**, the chat models, namely **AquilaChat2-7B**, **AquilaChat2-34B** and **AquilaChat2-70B**, as well as the long-text chat models, namely **AquilaChat2-7B-16k** and **AquilaChat2-34B-16k** The additional details of the Aquila model will be presented in the official technical report. Please stay tuned for updates on official channels. ## Quick Start ### 1. Inference ```python import torch from transformers import AutoTokenizer, AutoModelForCausalLM from transformers import BitsAndBytesConfig model_info = "BAAI/Aquila2-70B" tokenizer = AutoTokenizer.from_pretrained(model_info, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained(model_info, trust_remote_code=True) model.eval() text = "请给出10个要到北京旅游的理由。" tokens = tokenizer.encode_plus(text)['input_ids'] 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 Aquila2 series open-source model is licensed under [ BAAI Aquila Model Licence Agreement](https://huggingface.co/BAAI/Aquila2-70B/blob/main/BAAI-Aquila-Model-License-Agreement.pdf)