Downloads · 30 days
0
ccjjllt/qwen3.5-rouzhiba-lora
qwen3.5-rouzhiba-lora is a text generation model from ccjjllt. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
这是一个基于 Qwen/Qwen3.5-2B 使用弱智吧数据集进行 SFT 微调的 LoRA 模型。
Downloads · 30 days
0
Access
Public
Updated May 19, 2026
Repo size
87.3 MB
Likes
0
Public
Click a slice to open those files.
.safetensors67.3 MB · 77%
From the Hugging Face model README
这是一个基于 Qwen/Qwen3.5-2B 使用弱智吧数据集进行 SFT 微调的 LoRA 模型。
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
repo_id = "你的HF用户名/qwen3.5-2b-ruozhiba-lora"
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-2B", torch_dtype=torch.bfloat16, device_map="auto")
model = PeftModel.from_pretrained(base_model, repo_id)
tokenizer = AutoTokenizer.from_pretrained(repo_id)
# 接下来就可以正常推理了...