---
language:
- fr
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- summarizer
- 4bit
base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
---
# Uploaded as 4bit model
- **Developed by:** Labagaite
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-instruct-v0.2-bnb-4bit
# Training Logs
## Summary metrics
### Best ROUGE-1 score : **0.9842446709916588**
### Best ROUGE-2 score : **0.9842154131847726**
### Best ROUGE-L score : **0.9842446709916588**
## Wandb logs
You can view the training logs [](https://wandb.ai/william-derue/LLM-summarizer_trainer/runs/s9xqw6o8).
## Training details
### training data
- Dataset : [fr-summarizer-dataset](https://huggingface.co/datasets/Labagaite/fr-summarizer-dataset)
- Data-size : 7.65 MB
- train : 1.97k rows
- validation : 440 rows
- roles : user , assistant
- Format chatml "role": "role", "content": "content", "user": "user", "assistant": "assistant"
*French audio podcast transcription*
# Project details
[](https://github.com/WillIsback/Report_Maker)
Fine-tuned on French audio podcast transcription data for summarization task. As a result, the model is able to summarize French audio podcast transcription data.
The model will be used for an AI application: [Report Maker](https://github.com/WillIsback/Report_Maker) wich is a powerful tool designed to automate the process of transcribing and summarizing meetings.
It leverages state-of-the-art machine learning models to provide detailed and accurate reports.
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[](https://github.com/unslothai/unsloth)