使用transformers推理:
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
from peft import PeftModel
tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/baichuan-7B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("baichuan-inc/baichuan-7B", device_map="auto", trust_remote_code=True)
model = PeftModel.from_pretrained(model, "Laurie/baichuan-7b-lora-alpaca-cn")
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
query = "天空为什么是蓝色的?"
inputs = tokenizer(["<human>:{}\n<bot>:".format(query)], return_tensors="pt")
inputs = inputs.to("cuda")
generate_ids = model.generate(**inputs, max_new_tokens=256, streamer=streamer)
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.