| AquilaChat2 long-text chat model [AquilaChat2-34B-16k](https://github.com/FlagAI-Open/Aquila2#base-model-performance). | |
| Inference | |
| ``` | |
| from transformers import AutoTokenizer, AutoModelForCausalLM | |
| import torch | |
| device = torch.device("cuda:0") | |
| model_info = "h2oai/h2ogpt-16k-aquilachat2-34b" | |
| tokenizer = AutoTokenizer.from_pretrained(model_info, trust_remote_code=True) | |
| model = AutoModelForCausalLM.from_pretrained(model_info, trust_remote_code=True, torch_dtype=torch.bfloat16) | |
| model.eval() | |
| model.to(device) | |
| text = "Who are you?" | |
| from predict import predict | |
| out = predict(model, text, tokenizer=tokenizer, max_gen_len=200, top_p=0.95, | |
| seed=1234, topk=100, temperature=0.9, sft=True, device=device, | |
| model_name="h2oai/h2ogpt-16k-aquilachat2-34b") | |
| print(out) | |
| ``` | |
| License | |
| Aquila2 series open-source model is licensed under BAAI Aquila Model Licence Agreement | |