mistral-finetune

(★ 3,096)

No description available.

File Explorer

Download Latest Version (.zip)

- - bug_report.yml
  - config.yml
- 7B.yaml
- - __init__.py
  - args.py
  - data_loader.py
  - dataset.py
  - exceptions.py
  - tokenize.py
- - __init__.py
  - metrics_logger.py
  - utils.py
- __init__.py
- args.py
- checkpointing.py
- distributed.py
- eval.py
- loss.py
- mixed_precision.py
- utils.py
- wrapped_model.py
- __init__.py
- args.py
- lora.py
- moe.py
- rope.py
- transformer.py
- __init__.py
- test_checkpointer.py
- test_data.py
- test_mixed_precision.py
- test_model.py
- test_train_loop.py
- test_utils.py
- mistral_finetune_7b.ipynb
- __init__.py
- extend_model_vocab.py
- merge_lora.py
- reformat_data.py
- reformat_data_glaive.py
- validate_data.py
.gitignore
LICENSE
pyproject.toml
README.md
requirements.dev.txt
requirements.txt
train.py

# Installation Guide

1. Get the code

git clone https://github.com/mistralai/mistral-finetune

Downloads the entire project code from GitHub to your computer.

cd mistral-finetune

Moves into the project folder you just downloaded.

2. Official Install Script

Easy Recommended

Prerequisites

Python 3 Python is required to use pip.

pip install mistral_inference

Installs the package published on PyPI directly — no need to clone the source.

pip install wandb

Installs the package published on PyPI directly — no need to clone the source.

✅ After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.

Pulled directly from this repo's README.

3. Python

Easy

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

pip install -r requirements.txt

Installs the Python libraries listed in requirements.txt (or similar).

python -m utils.validate_data --train_yaml example/7B.yaml

Runs the Python script (or module).

python -m utils.reformat_data $HOME/data/ultrachat_chunk_train.jsonl

Runs the Python script (or module).

python -m utils.reformat_data $HOME/data/ultrachat_chunk_eval.jsonl

Runs the Python script (or module).

python -m utils.reformat_data_glaive $HOME/data/glaive_train.jsonl

Runs the Python script (or module).

✅ If it runs without errors and prints output in the terminal, it worked.

Pulled directly from this repo's README.