Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


saqr-7b-merged - bnb 4bits
- Model creator: https://huggingface.co/Menouar/
- Original model: https://huggingface.co/Menouar/saqr-7b-merged/




Original model description:
---
library_name: transformers
tags:
- saqr-7b-instrcut
- Pytorch
license: apache-2.0
datasets:
- HuggingFaceH4/ultrachat_200k
- openbmb/UltraFeedback
- gsm8k
language:
- en
pipeline_tag: text-generation
---

# saqr-7b-merged

This model is a merged version of [**saqr-7b-instruct**](https://huggingface.co/Menouar/saqr-7b-instruct) with LoRA Adapters.


<img src="https://huggingface.co/Menouar/saqr-7b-instruct/resolve/main/saqr.jpg" alt="Saqr Logo" width="800" style="margin-left:auto; margin-right:auto; display:block;"/>