---
language:
- en
library_name: transformers
tags:
- auto-gptq
- AutoRound
license: apache-2.0
---


*Note: This model works well only for simple coding problems involving short sequences of tokens. For a better model, use [the 4-bit version](https://huggingface.co/kaitchup/Qwen2.5-Coder-32B-Instruct-AutoRound-GPTQ-4bit).*

## Model Details

This is [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) quantized with [AutoRound](https://github.com/intel/auto-round/tree/main) (symmetric quantization) and serialized with the GPTQ format in 2-bit. The model has been created, tested, and evaluated by The Kaitchup.

Details on the quantization process and how to use the model here:
[The Recipe for Extremely Accurate and Cheap Quantization of 70B+ LLMs](https://kaitchup.substack.com/p/the-recipe-for-extremely-accurate-quantization)


- **Developed by:** [The Kaitchup](https://newsletter.kaitchup.com/)
- **Language(s) (NLP):** English
- **License:** Apache 2.0 license