Instructions to use splinter0711/sarvam-translate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use splinter0711/sarvam-translate 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="splinter0711/sarvam-translate")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("splinter0711/sarvam-translate") model = AutoModelForMultimodalLM.from_pretrained("splinter0711/sarvam-translate", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from splinter0711/sarvam-translate: direct link, hf CLI and curl.
- Browser
- Download file 70 Bytes
-
https://huggingface.co/splinter0711/sarvam-translate/resolve/main/processor_config.json
- Command line
-
hf download hf://splinter0711/sarvam-translate/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/splinter0711/sarvam-translate/resolve/main/processor_config.json
70 Bytes
| { | |
| "image_seq_length": 256, | |
| "processor_class": "Gemma3Processor" | |
| } | |