Edit model card

Uploaded as 4bit 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

Downloads last month
5
Safetensors
Model size
3.64B params
Tensor type
F32
FP16
U8
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Labagaite/llama-Summarizer-2-7b-chat-bnb-4bit

Quantized
(8)
this model