Llama 3.2 正式支援 Keras：跨框架輕鬆微調與部署 Meta 最新輕量級模型
Original: “Llama 3.2 in Keras”
Meta's Llama 3.2 release includes lightweight 1B and 3B text models designed specifically for edge computing and mobile devices. These…
Hugging Face 與 Keras 團隊宣布 Llama 3.2 模型正式登陸 Keras 生態系。開發者現在可以透過 KerasNLP 輕鬆載入 Llama 3.2 的 1B 與 3B 輕量級模型。得益於 Keras 3 的多後端架構，使用者能自由切換 JAX、PyTorch 或 TensorFlow，並利用 LoRA 等技術進行高效微調與跨平台部署。
Meta's Llama 3.2 release includes lightweight 1B and 3B text models designed specifically for edge computing and mobile devices. These models have now been officially integrated into the Keras ecosystem through a collaboration between Hugging Face and the Keras team, allowing developers to invoke them directly via KerasNLP (Keras Hub).
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Hugging Face Blog →Summaries are AI-generated; the original article is authoritative.