Instructions to use NifeLab/pib-indic-en-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use NifeLab/pib-indic-en-v1 with PEFT:
Task type is invalid.
- Transformers
How to use NifeLab/pib-indic-en-v1 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="NifeLab/pib-indic-en-v1", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("NifeLab/pib-indic-en-v1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_summary.json from NifeLab/pib-indic-en-v1: direct link, hf CLI and curl.
- Browser
- Download file 270 Bytes
-
https://huggingface.co/NifeLab/pib-indic-en-v1/resolve/main/eval_summary.json
- Command line
-
hf download hf://NifeLab/pib-indic-en-v1/eval_summary.json
-
curl -L -o eval_summary.json https://huggingface.co/NifeLab/pib-indic-en-v1/resolve/main/eval_summary.json
270 Bytes
| { | |
| "direction": "indic-en", | |
| "version": "v1", | |
| "metrics": { | |
| "bleu": 13.38, | |
| "chrf": 34.82, | |
| "translated": 3, | |
| "total": 3, | |
| "latency_ms_p50": 43833.6 | |
| }, | |
| "promoted": true, | |
| "reason": "No existing production model \u2014 first model auto-promoted" | |
| } |