---
language:
- en
library_name: transformers
license: cc-by-4.0
tags:
- auto-gptq
- AutoRound
---


## Model Details

This is [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) quantized with [AutoRound](https://github.com/intel/auto-round) to 4-bit and symmetric quantization for compatibility with Marlin. The model has been created, tested, and evaluated by The Kaitchup.

Details on quantization process, evaluation, and how to use the model here: [Fine-tuning Phi-3.5 MoE and Mini on Your Computer](https://kaitchup.substack.com/p/fine-tuning-phi-35-moe-and-mini-on)


- **Developed by:** [The Kaitchup](https://kaitchup.substack.com/)
- **Language(s) (NLP):** English
- **License:** cc-by-4.0