Training pipelines and the inference engine for Firefox Translations machine translation models. The trained models are hosted in a public Google Cloud Storage bucket (see Model Registry UI and JSON).
A translation model that fits in 440 megabytes, runs entirely offline, and handles 33 languages just landed on Hugging Face, courtesy of Tencent. The model, called Hy-MT1.5-1.8B-1.25bit-GGUF, supports ...
Context window management. Learn how to effectively manage context windows in Llama workflows to reduce latency and improve ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results