AquilaChat2 long-text chat model AquilaChat2-34B-16k.
Inference
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
device = torch.device("cuda:0")
model_info = "BAAI/AquilaChat2-34B-16k"
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 = "请给出10个要到北京旅游的理由。"
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="AquilaChat2-34B-16K")
print(out)
License Aquila2 series open-source model is licensed under BAAI Aquila Model Licence Agreement