---
base_model: unsloth/qwen3-14b-unsloth
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
- reasoning
- math
- code-generation
license: apache-2.0
language:
- en
datasets:
- open-thoughts/OpenThoughts2-1M
library_name: transformers
---


![image](./image.png)
# Qwen3-14B-Griffon

**Developed by:** Daemontatox  
**License:** Apache-2.0  
**Finetuned from:** [unsloth/qwen3-14b-unsloth](https://huggingface.co/unsloth/qwen3-14b-unsloth)

## Model Overview

This is a fine-tuned version of the Qwen3-14B model using the high-quality **OpenThoughts2-1M** dataset. Fine-tuned with Unsloth’s TRL-compatible framework and LoRA for efficient performance, this model is optimized for **advanced reasoning tasks**, especially in **math**, **logic puzzles**, **code generation**, and **step-by-step problem solving**.

## Training Dataset

- **Dataset:** [OpenThoughts2-1M](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M)  
- **Source:** A synthetic dataset curated and expanded by the OpenThoughts team  
- **Volume:** ~1.1M high-quality examples  
- **Content Type:** Multi-turn reasoning, math proofs, algorithmic code generation, logical deduction, and structured conversations  
- **Tools Used:** [Curator Viewer](https://curator.bespokelabs.ai/)  

This dataset builds upon OpenThoughts-114k and integrates strong reasoning-centric data sources like OpenR1-Math and KodCode.

## Intended Use

This model is particularly suited for:

- Chain-of-thought and step-by-step reasoning  
- Code generation with logical structure  
- Educational tools for math and programming  
- AI agents requiring multi-turn problem-solving  

## Limitations

- English-only focus (does not generalize well to other languages)  
- May hallucinate factual content despite reasoning depth  
- Inherits possible biases from synthetic pretraining data  

## Example Usage

```python
# Use a pipeline as a high-level helper
from transformers import pipeline

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="Daemontatox/Qwen3_14B_Griffon")
pipe(messages)

```
## Training Details

# Framework: TRL + LoRA with Unsloth acceleration

# Epochs/Steps: Custom fine-tuning on ~1M samples

# Hardware: Single-node A100 80GB / similar high-VRAM setup

# Objective: Enhance multi-domain reasoning under compute-efficient constraints



---