sr5434's picture
Update README.md
ab9ce4e verified
|
raw
history blame
298 Bytes
metadata
license: mit
language:
  - fr

This model is a LoRA for using Llama 2 13b Chat in French. Thanks to David Hall and his team at Stanford's CRFM lab for Levanter, which I used to train my model. Also, thank you to the TensorFlow Research Cloud for providing the TPU v4-8 that I used in training.