qwen3-4b-sft-5k-mix-merged
This repository provides a merged FP16 model fine-tuned from
Qwen/Qwen3-4B-Instruct-2507 using QLoRA (Unsloth).
Training Objective
This model is trained to improve structured output accuracy
(JSON / YAML / XML / TOML / CSV).
Loss is applied only to the final assistant output,
while intermediate reasoning (Chain-of-Thought) is masked.
Training Configuration
- Base model: Qwen/Qwen3-4B-Instruct-2507
- Method: QLoRA (4-bit), merged to FP16
- Max sequence length: 1024
- Epochs: 1
- Learning rate: 1e-3
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "yuk1chan/qwen3-4b-sft-5k-mix-merged"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.float16,
device_map="auto",
)
Sources & Terms (IMPORTANT)
Training data: daichira/structured-5k-mix-sft
Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.
