---
language:
- en
license: apache-2.0
tags:
- gguf
- code
- reasoning
- agentic
- qwen2
- dpo
- llama.cpp
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
pipeline_tag: text-generation
---

# MalxLabs-Fable5_QwenCoder (Fable-Coder-7B-DPO)

<div align="center">

[![GitHub](https://img.shields.io/badge/GitHub-Repository-black.svg?logo=github)](https://github.com/YoMosa2009/MalxLabs-Fable5_QwenCoder)
[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
[![Format](https://img.shields.io/badge/Format-Q4__K__M_GGUF-orange.svg)](#model-details)
[![Benchmark Score](https://img.shields.io/badge/Benchmark_Score-80.0%25_(92%2F115)-indigo.svg)](#benchmark-performance)

**A specialized 4.36 GB Q4_K_M GGUF model optimized for multi-turn agent tool execution and logical programming correctness.**

[🐙 GitHub Benchmark & Harness](https://github.com/YoMosa2009/MalxLabs-Fable5_QwenCoder) • [📊 Findings & Transcripts](https://github.com/YoMosa2009/MalxLabs-Fable5_QwenCoder/blob/main/FINDINGS.md)

</div>

---

## Overview

**Fable-Coder-7B-DPO** is an aligned, post-trained derivative of `Qwen/Qwen2.5-Coder-7B-Instruct`. It was specifically tuned to eliminate arithmetic hallucinations, handle strict constraints, and reliably execute tool paths in autonomous agent workflows.

In a closed comparative benchmark of 33 tasks across 7 domains against its base model, Fable-Coder scored **92/115 (80.0%)** versus **88/115 (76.5%)** for `Qwen2.5-Coder-7B-Instruct`, demonstrating a **+20.0% improvement in complex reasoning** while matching baseline coding capability.

---

## Architectural Pipeline Flow

```
[Base Model: Qwen2.5-Coder-7B] (Natively Loaded in BF16 Precision)
│
▼
[Stage 1: Multi-Turn SFT with LoRA] ──► Adapts agent behavioral trajectories via ChatML
│
▼
[Stage 2: Direct Preference Optimization] ──► Aligns tool call decisions & correct syntax
│
▼
[Stage 3: Full FP16 Parameter Merge] ──► Fuses low-rank adapters back into base model
│
▼
[Stage 4: Tokenizer & GGUF Compilation] ──► Converts PyTorch checkpoint to GGUF format
│
▼
[Stage 5: Q4_K_M CMake Quantization] ──► Compresses FP16 parameters to 4.36 GB binary
```

### Key Training Highlights
1. **Supervised Fine-Tuning (SFT) with LoRA**: Injected LoRA matrices (r=8, alpha=16) targeting attention projection layers (`q_proj`, `v_proj`) using actual agent trajectories from `MoreThought/Fable-5.1-Max-Reasoning-Filtered-5000x`.
2. **Direct Preference Optimization (DPO)**: Pairwise dataset contrasting clean, efficient tool invocations against redundant loops and lazy stubs (positive reward margin peak: 0.01457).
3. **Full FP16 Merge & Tokenizer Patch**: Fused weights into native BF16 base and patched tokenizer configuration for clean GGUF compilation.
4. **CMake Q4_K_M Quantization**: Compressed the 14.5 GB weights to a single-file **4.36 GB binary** (~70% storage reduction), fitting within ~5.1 GB VRAM on consumer GPUs.

---

## Benchmark Comparison

| Category | Fable-Coder-7B-DPO | Qwen2.5-Coder-7B-Instruct | Delta |
|---|:---:|:---:|:---:|
| **Overall Score** | **92 / 115 (80.0%)** | 88 / 115 (76.5%) | **+4 pts (+3.5%) Fable** |
| **Reasoning** | **17 / 20 (85.0%)** | 13 / 20 (65.0%) | **+4 pts (+20.0%) Fable** |
| **Coding** | 25 / 35 (71.4%) | 25 / 35 (71.4%) | Tied |
| **Agentic Planning** | 21 / 25 (84.0%) | 21 / 25 (84.0%) | Tied |
| **Security** | 9 / 11 (81.8%) | 9 / 11 (81.8%) | Tied |
| **Knowledge** | 8 / 8 (100.0%) | 8 / 8 (100.0%) | Tied |
| **Context Retention** | 6 / 6 (100.0%) | 6 / 6 (100.0%) | Tied |

---

## Quickstart & Usage

### Using `llama.cpp`
```bash
llama-cli -m fable-coder-7b-dpo.Q4_K_M.gguf -p "Write a Python function to merge intervals without mutating the input." -n 512
```

### Using `huggingface-cli`
```bash
huggingface-cli download MalxTech/MalxLabs-Fable5_QwenCoder fable-coder-7b-dpo.Q4_K_M.gguf --local-dir .
```

### Using Ollama
Create a `Modelfile`:
```dockerfile
FROM ./fable-coder-7b-dpo.Q4_K_M.gguf
TEMPLATE """<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""
PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"
```
Then build and run:
```bash
ollama create fable-coder -f Modelfile
ollama run fable-coder
```

---

## Citation & Acknowledgments
* Base model: [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct)
* SFT dataset: [MoreThought/Fable-5.1-Max-Reasoning-Filtered-5000x](https://huggingface.co/datasets/MoreThought/Fable-5.1-Max-Reasoning-Filtered-5000x)
* Full benchmark repository: [YoMosa2009/MalxLabs-Fable5_QwenCoder](https://github.com/YoMosa2009/MalxLabs-Fable5_QwenCoder)