README.md

---
license: apache-2.0
datasets:
- Laurie/alpaca_chinese_dataset
language:
- zh
- en
metrics:
- accuracy
library_name: transformers
pipeline_tag: text2text-generation
---
## Usage:

    from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
    import torch
    tokenizer = AutoTokenizer.from_pretrained("baichuan7b-lora-merged", trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained("baichuan7b-lora-merged", device_map="auto", trust_remote_code=True,torch_dtype=torch.float16)
    streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
    
    query = "爆炒钢筋水泥怎么做才好吃？"
    
    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)