Training

• Method: LoRA (r=16, alpha=32), BF16
• Data: coffee-sft-dataset (80/10/10 train/val/test split)
• Epochs: 3
• Hardware: RTX 4060 8GB
• Framework: TRL SFTTrainer + PEFT

Usage

python
Copy code
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained(
    "openbmb/MiniCPM5-1B",
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True
)
model = PeftModel.from_pretrained(base, "ynanxiu/minicpm5-coffee-lora")
tokenizer = AutoTokenizer.from_pretrained("openbmb/MiniCPM5-1B", trust_remote_code=True)

messages = [{"role": "user", "content": "阿拉比卡和罗布斯塔的区别是什么？"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Framework versions

• PEFT 0.19.1
• TRL 0.24.0
• Transformers 5.5.0
• PyTorch 2.6.0+cu124