Text Generation
llama
pretrained
llama-3
openllm-france
Jeronymous's picture
Update README.md
630004b verified
|
raw
history blame
1.2 kB
metadata
license: apache-2.0
pipeline_tag: text-generation
language:
  - fr
  - en
  - it
  - de
  - es
tags:
  - pretrained
  - llama-3
  - openllm-france
datasets:
  - OpenLLM-France/Lucie-Training-Dataset
widget:
  - text: |-
      Quelle est la capitale de l'Espagne ? Madrid.
      Quelle est la capitale de la France ?
    example_title: Capital cities in French
    group: 1-shot Question Answering

Model Card

This repository contains checkpoints (splitted for 512 GPUs) in DeepSpeed format for the Lucie-7B model, which was trained using this repository of code based on a fork of Megatron-Deepspeed.

Each checkpoint is in a subbranch (revision), which names specifies the number of training steps. For instance step0400000 corresponds to the checkpoint after 4M training steps.

Those checkpoints are provided so that the model can be retrained from a given point.

Contact

[email protected]