Modelpublic

ahmetggg/Luck-Qwen3-4b-Code-FineTune

sourceHugging Faceapache-2.0updated 23d agoView on Hugging Face

1likes311downloads

Model Card

Luck-Qwen3-4b-Code-FineTune

A QLoRA fine-tune of unsloth/Qwen3-4B-Instruct-2507 specialized in agentic coding, multi-step reasoning, tool use, and calibrated uncertainty.

TL;DR: This model improves output formatting consistency, tool interaction, and knowledge boundary awareness ("I don't know" responses) without increasing the underlying capability ceiling of the base model.

<img src="training_loss.png" alt="Training Loss Curve" width="100%"> Training loss convergence from ~1.7 to ~0.55 across 1,267 steps.

Model Summary

Parameter / Metric	Value
Base Model	`unsloth/Qwen3-4B-Instruct-2507` (4.05B params, dense)
Method	QLoRA (4-bit NF4)
LoRA Rank / Alpha	r=16, alpha=16, dropout=0
Target Modules	`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`
Trainable Parameters	33,030,144 / 4,055,498,240 (0.81%)
Context Length	4,096 tokens
Dataset Size	10,129 examples
Training Steps / Epochs	1,267 steps / 1 epoch
Effective Batch Size	8 (2 per-device × 4 gradient accumulation steps)
Optimizer / Schedule	`adamw_8bit`, learning rate 2e-4, cosine schedule
Hardware	Single T4 GPU (Google Colab / Kaggle)
Final Loss	~0.55 (started at ~1.7)
Frameworks	Unsloth, TRL (`SFTTrainer`), PEFT, Transformers

In This Repo

This repository contains:

—QLoRA LoRA Adapter weights
—Merged FP16 safetensors weights

Note: Quantized GGUF files are hosted separately at [`ahmetggg/Luck-Qwen3-4b-Code-FineTune-GGUF`](https://huggingface.co/ahmetggg/Luck-Qwen3-4b-Code-FineTune-GGUF).

Intended Use

—Agentic Coding: Repository-level navigation, issue resolution, and code generation.
—Multi-Step Reasoning: Step-by-step problem-solving in science and math domains.
—Tool Use: Structured multi-turn function and tool calling.
—Calibrated Uncertainty: Refusing to answer ("I don't know") when encountering actual knowledge gaps.

Training Data

Source	Focus Area	Details / Filtering
`nvidia/Open-SWE-Traces`	Agentic coding	Filtered exclusively to `resolved == 1` trajectories
`open-thoughts/OpenThoughts3-1.2M`	Math & science reasoning	Code domain excluded (handled by Open-SWE-Traces)
`Agent-Ark/Toucan-1.5M`	Tool calling	Real multi-turn tool interaction trajectories
Custom R-Tuning Set	Calibration	~150–300 MMLU items queried on base model; correct outputs retained as normal QA, incorrect outputs relabeled as "I don't know"

Usage

Option 1: Unsloth (LoRA Adapter)

python

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "ahmetggg/Luck-Qwen3-4b-Code-FineTune",
    max_seq_length = 4096,
    load_in_4bit = True,
)
FastLanguageModel.for_inference(model)

messages = [{"role": "user", "content": "Write a Python function to reverse a linked list."}]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))