Instructions to use ai4bharat/IndicBARTSS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ai4bharat/IndicBARTSS with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("ai4bharat/IndicBARTSS") model = AutoModelForSeq2SeqLM.from_pretrained("ai4bharat/IndicBARTSS", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Added YAML metadata: languages, license, pipeline tag
#2
by Sanjjjayyy - opened
README.md
CHANGED
|
@@ -1,3 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
IndicBARTSS is a multilingual, sequence-to-sequence pre-trained model focusing on Indic languages and English. It currently supports 11 Indian languages and is based on the mBART architecture. You can use IndicBARTSS model to build natural language generation applications for Indian languages by finetuning the model with supervised training data for tasks like machine translation, summarization, question generation, etc. Some salient features of the IndicBARTSS are:
|
| 2 |
|
| 3 |
<ul>
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- as
|
| 4 |
+
- bn
|
| 5 |
+
- en
|
| 6 |
+
- gu
|
| 7 |
+
- hi
|
| 8 |
+
- kn
|
| 9 |
+
- ml
|
| 10 |
+
- mr
|
| 11 |
+
- or
|
| 12 |
+
- pa
|
| 13 |
+
- ta
|
| 14 |
+
- te
|
| 15 |
+
license: mit
|
| 16 |
+
tags:
|
| 17 |
+
- mbart
|
| 18 |
+
- indic-languages
|
| 19 |
+
- multilingual
|
| 20 |
+
- text2text-generation
|
| 21 |
+
- sequence-to-sequence
|
| 22 |
+
- AI4Bharat
|
| 23 |
+
pipeline_tag: text2text-generation
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
IndicBARTSS is a multilingual, sequence-to-sequence pre-trained model focusing on Indic languages and English. It currently supports 11 Indian languages and is based on the mBART architecture. You can use IndicBARTSS model to build natural language generation applications for Indian languages by finetuning the model with supervised training data for tasks like machine translation, summarization, question generation, etc. Some salient features of the IndicBARTSS are:
|
| 27 |
|
| 28 |
<ul>
|