# Hugging Face — “Llama 3.2 in Keras”

- Company: Hugging Face (huggingface.co)
- Announced: 2024-10-21T00:00:00+00:00
- Category: capability-change
- Subject: Platform
- Open weights: yes
- Models affected: Llama 3.2, Llama-3.2-1B-Instruct
- Source: https://huggingface.co/blog/keras-llama-32
- Record: https://forck.live/items/1813-llama-3-2-in-keras

This blog post announces that Llama 3.2 models are already supported in Keras, as Keras Llama3 can load from any standard Hugging Face checkpoint, including Llama 3.2 checkpoints. It provides a code example and discusses Keras features like multi-backend, tokenizer, and fine-tuning.

## Evidence

Verbatim from https://huggingface.co/blog/keras-llama-32:

> Keras Llama3 can be loaded from any standard (i.e. safetensors) Hugging Face checkpoint, including the 3.2 checkpoints.

---

Record: https://forck.live/items/1813-llama-3-2-in-keras
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md