qwen3-4b-struct-exp89

This model is a fine-tuned version of curio184/qwen3-4b-struct-exp77 with SFT + Anti-Codefence DPO (lr=5e-07, beta=0.1).

This repository contains the full merged 16-bit weights.

Training Configuration

• Base model: curio184/qwen3-4b-struct-exp77
• Dataset: u-10bei/structured_data_with_cot_dataset_512_v2
• Method: SFT + Anti-Codefence DPO (lr=5e-07, beta=0.1)
• LoRA: r=16, alpha=32
• DoRA: True

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "curio184/qwen3-4b-struct-exp89"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto",
)

Sources & Terms (IMPORTANT)

Training data: u-10bei/structured_data_with_cot_dataset_512_v2

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.