Instructions to use MalxTech/MalxLabs-Fable5_QwenCoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use MalxTech/MalxLabs-Fable5_QwenCoder with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M

Use Docker

docker model run hf.co/MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use MalxTech/MalxLabs-Fable5_QwenCoder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MalxTech/MalxLabs-Fable5_QwenCoder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MalxTech/MalxLabs-Fable5_QwenCoder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M

Ollama
How to use MalxTech/MalxLabs-Fable5_QwenCoder with Ollama:
```
ollama run hf.co/MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M
```
Unsloth Desktop

How to use MalxTech/MalxLabs-Fable5_QwenCoder with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use MalxTech/MalxLabs-Fable5_QwenCoder with Docker Model Runner:
```
docker model run hf.co/MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M
```

Lemonade

How to use MalxTech/MalxLabs-Fable5_QwenCoder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M

Run and chat with the model

lemonade run user.MalxLabs-Fable5_QwenCoder-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use MalxTech/MalxLabs-Fable5_QwenCoder with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use MalxTech/MalxLabs-Fable5_QwenCoder with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "MalxTech/MalxLabs-Fable5_QwenCoder:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MalxLabs-Fable5_QwenCoder / README.md

MalxTech

docs: initial model card and pipeline report

39d7ce9 verified about 2 months ago

preview code

Raw History Blame Contribute Delete

4.71 kB

---
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)

	---
	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)