---
library_name: transformers
license: apache-2.0
language:
- fr
- en
---


# Gabriel-8x7b-Instruct-gguf-v0.1

<!-- Provide a quick summary of what the model is/does. -->
Quantized version of HelloBible/Gabriel-8x7B-Instruct-v0.1

<!-- Provide a longer summary of what this model is. -->

A selection of quantizations of [Gabriel-8x7B-Instruct-v0.1](https://huggingface.co/Hello-Bible/Gabriel-8x7B-Instruct-v0.1), made using llama.cpp version: 3277 (5fac350b)

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->


## original model card

<!-- Provide a quick summary of what the model is/does. -->


<!-- Provide a longer summary of what this model is. -->

Gabriel-8x7B-Instruct-v0.1 is a fine tuned model using a 36k French/English Christian dataset (self made).

Base model used for training: [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->