M2M100 418M Custom

This is a custom-hosted version of Facebook's m2m100_418M multilingual translation model, deployed for reliable API-based inference.

πŸ“Œ Model Summary

  • Base Model: facebook/m2m100_418M
  • Supports 100 languages
  • Many-to-many multilingual translation
  • Hosted with custom handler.py for reliable inference endpoint support

πŸ”§ Usage

You can use this model through a Hugging Face Inference Endpoint or with the transformers library directly:

from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
model = M2M100ForConditionalGeneration.from_pretrained("Raahulthakur/m2m100_418M_custom")
tokenizer = M2M100Tokenizer.from_pretrained("Raahulthakur/m2m100_418M_custom")
Downloads last month
13
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support