![]() ![]() We support every MT model in the □ Hugging Face's Hub. NLLB can directly translate between +40,000 of +200 languages.įacebook/nllb-moe-54b: (Requires transformers 4.28.0) It was introduced in this paper and first released in this repository. It aims to help people communicate with anyone, anywhere, regardless of their language preferences. No Language Left Behind (NLLB) open-sources models capable of delivering high-quality translations directly between any pair of 200+ languages - including low-resource languages like Asturian, Luganda, Urdu and more. M2M100 can directly translate between 9,900 directions of 100 languages. M2M100 is a multilingual encoder-decoder (seq-to-seq) model trained for Many-to-Many multilingual translation introduced in this paper and first released in this repository. You can also see the examples folder for examples of how to use EasyTranslate with different models. We still recommend you to use M2M100 or NLLB200 for the best results, but you can experiment with any other MT model, as well as prompting LLMs to generate translations (See Prompting Section for more details). □ EasyTranslate now supports any Seq2SeqLM (m2m100, nllb200, small100, mbart, MarianMT, T5, FlanT5, etc.) and any CausalLM (GPT2, LLaMA, Vicuna, Falcon) model from □ Hugging Face's Hub!! See the Supported languages table for a table of the supported languages and their ids. Test the □ Online Demo here: Supported languages □ Prompt support! See Prompting for more information.□ Support for any Seq2SeqLM or CausalLM model from HuggingFace's Hub.See Loading Huge Models for more information. □ Load huge models in a single GPU with 8-bits / 4-bits quantization and support for splitting the model between GPU and CPU.See Decoding Strategies for more information. Multiple decoding strategies: Greedy Search, Beam Search, Top-K Sampling, Top-p (nucleus) sampling, etc.Set an initial batch size, if it doesn't fit, we will automatically adjust it. Automatic batch size finder: Forget CUDA OOM errors.BF16 / FP16 / FP32 / 8 Bits / 4 Bits precision.CPU / multi-CPU / GPU / multi-GPU / TPU acceleration.We also provide a script for Easy-Evaluation of your translations □Įasy-Translate is built on top of □HuggingFace's Transformers and □HuggingFace's Accelerate library. We support almost any model, including M2M100, Easy-Translate is designed to be as easy as possible for beginners and as seamless and customizable as possible for advanced users. Easy-Translate is a script for translating large text files with a □SINGLE COMMAND□. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |