XAT928/qwen3-1.7b-sft-lora-20250923

LoRA adapter for Qwen/Qwen3-1.7B-Base (Japanese SFT).

Summary

• Base model: Qwen/Qwen3-1.7B-Base
• Adapter type: LoRA (PEFT; saved via save_pretrained)
• Exported: 2025-09-24 14:55:39

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-1.7B-Base", torch_dtype=torch.bfloat16)
tok  = AutoTokenizer.from_pretrained("Qwen/Qwen3-1.7B-Base", use_fast=True)

model = PeftModel.from_pretrained(base, "XAT928/qwen3-1.7b-sft-lora-20250923")
model.eval()

prompt = "次の問いに丁寧で簡潔に答えてください。\n\nQ: 富士山の標高は？"
inputs = tok(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    out = model.generate(**inputs, max_new_tokens=128)
print(tok.decode(out[0], skip_special_tokens=True))