Translation
Transformers
PyTorch
Safetensors
IndicTrans
text2text-generation
indictrans2
ai4bharat
multilingual
custom_code
Instructions to use ai4bharat/indictrans2-indic-en-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ai4bharat/indictrans2-indic-en-1B with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="ai4bharat/indictrans2-indic-en-1B", trust_remote_code=True)# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("ai4bharat/indictrans2-indic-en-1B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Missing tokenizer
#1
by zuhashaik - opened
There is a missing tokenizer in this repo try to update it, it'll be usefull
Our tokenizers are not compatible with the transformers.AutoTokenizer class. We have provided the instructions and custom tokenizers in the github repo.
zuhashaik changed discussion status to closed
The custom tokenizer script is missing from the github repo, can you please help even the uri is not working