test-lora.py

import os
from unsloth import FastLanguageModel
import torch
from transformers import TextStreamer

if True:
    from unsloth import FastLanguageModel
    model, tokenizer = FastLanguageModel.from_pretrained(
        model_name = "lora_model", # 加载训练后的LoRA模型
        max_seq_length = 2048,
        dtype = None,
        load_in_4bit = True,
    )
    FastLanguageModel.for_inference(model) 
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{}
### Input:
{}
### Response:
{}"""

inputs = tokenizer(
[
    alpaca_prompt.format(
        "请用中文回答", 
        "告诉我冻结法的原理。", 
        "", 
    )
], return_tensors = "pt").to("cuda")

text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)