---
base_model: unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
license: mit
language:
- en
datasets:
- bespokelabs/Bespoke-Stratos-17k
- open-thoughts/OpenThoughts-114k
- angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k
- allenai/ai2_arc
- allenai/hellaswag
- Rowan/hellaswag
- TIGER-Lab/MMLU-Pro
- CohereLabs/Global-MMLU
---

# Uploaded finetuned  model

- **Developed by:** NovatasticRoScript
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit

1st teacher model for upcoming **Atomight-V2.2**, we'll be released soon. 
Future teacher mdoels:
*UltraMath*, 
*UltraCode*, 
*UltraBench*, 
and more.. 

This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)