Labagaite's picture
Upload README.md with huggingface_hub
885f952 verified
metadata
language:
  - fr
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - summarizer
  - lora
base_model: unsloth/llama-2-7b-chat-bnb-4bit

Uploaded as lora model

  • Developed by: Labagaite
  • License: apache-2.0
  • Finetuned from model : unsloth/llama-2-7b-chat-bnb-4bit

Training Logs

Summary metrics

Best ROUGE-1 score : 0.007804878048780488

Best ROUGE-2 score : 0

Best ROUGE-L score : 0.005853658536585366

Wandb logs

You can view the training logs .

Training details

training data

  • Dataset : 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

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 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 llama model was trained 2x faster with Unsloth and Huggingface's TRL library. This llama was trained with LLM summarizer trainer LLM summarizer trainer