Summarization
Transformers
PyTorch
Safetensors
bart
text2text-generation
Generated from Trainer
hindi
seq2seq
Instructions to use Someman/bart-hindi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Someman/bart-hindi with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" 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("summarization", model="Someman/bart-hindi")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Someman/bart-hindi") model = AutoModelForSeq2SeqLM.from_pretrained("Someman/bart-hindi", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from Someman/bart-hindi: direct link, hf CLI and curl.
- Browser
- Download file 280 Bytes
-
https://huggingface.co/Someman/bart-hindi/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://Someman/bart-hindi/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/Someman/bart-hindi/resolve/main/special_tokens_map.json
280 Bytes
| { | |
| "bos_token": "<s>", | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "mask_token": { | |
| "content": "<mask>", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": "<pad>", | |
| "sep_token": "</s>", | |
| "unk_token": "<unk>" | |
| } | |