Instructions to use NifeLab/pib-en-indic-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use NifeLab/pib-en-indic-v1 with PEFT:
Task type is invalid.
- Transformers
How to use NifeLab/pib-en-indic-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-en-indic-v1", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("NifeLab/pib-en-indic-v1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_summary.json from NifeLab/pib-en-indic-v1: direct link, hf CLI and curl.
- Browser
- Download file 255 Bytes
-
https://huggingface.co/NifeLab/pib-en-indic-v1/resolve/main/eval_summary.json
- Command line
-
hf download hf://NifeLab/pib-en-indic-v1/eval_summary.json
-
curl -L -o eval_summary.json https://huggingface.co/NifeLab/pib-en-indic-v1/resolve/main/eval_summary.json
255 Bytes
| { | |
| "direction": "en-indic", | |
| "version": "v2", | |
| "metrics": { | |
| "bleu": 24.61, | |
| "chrf": 47.6, | |
| "translated": 7, | |
| "total": 7, | |
| "latency_ms_p50": 16987.9 | |
| }, | |
| "promoted": true, | |
| "reason": "BLEU 24.6 \u2265 14.2 and chrF 47.6 \u2265 31.2" | |
| } |