Downloads · 30 days
6
2% of all-time downloads
RegFo/Matsuo2025-Main-Qwen3-4B-SFT-T4-v1
Matsuo2025-Main-Qwen3-4B-SFT-T4-v1 is a text generation model from RegFo. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This repository provides a LoRA adapter fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using QLoRA (4-bit, Unsloth) on NVIDIA T4 GPU.
Downloads · 30 days
6
2% of all-time downloads
All-time downloads
345
Public
Repo size
1.1 GB
Likes
0
Public
Click a slice to open those files.
.safetensors529 MB · 97%
From the Hugging Face model README
This repository provides a LoRA adapter fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using QLoRA (4-bit, Unsloth) on NVIDIA T4 GPU.
This is a baseline model to ensure reproducibility on Colab Free tier.
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch
base = "Qwen/Qwen3-4B-Instruct-2507"
# ★変更点: T4版のIDを指定
adapter = "RegFo/Matsuo2025-Main-Qwen3-4B-SFT-T4-v1"
tokenizer = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(
base,
torch_dtype=torch.float16,
device_map="auto",
)
model = PeftModel.from_pretrained(model, adapter)