Instructions to use Azma-AI/bart-conversation-summarizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Azma-AI/bart-conversation-summarizer 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="Azma-AI/bart-conversation-summarizer")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Azma-AI/bart-conversation-summarizer") model = AutoModelForSeq2SeqLM.from_pretrained("Azma-AI/bart-conversation-summarizer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from Azma-AI/bart-conversation-summarizer: direct link, hf CLI and curl.
- Browser
- Download file 390 Bytes
-
https://huggingface.co/Azma-AI/bart-conversation-summarizer/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://Azma-AI/bart-conversation-summarizer/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/Azma-AI/bart-conversation-summarizer/resolve/main/tokenizer_config.json
390 Bytes
| { | |
| "add_prefix_space": false, | |
| "bos_token": "<s>", | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "errors": "replace", | |
| "mask_token": "<mask>", | |
| "model_max_length": 1024, | |
| "name_or_path": "facebook/bart-large-xsum", | |
| "pad_token": "<pad>", | |
| "sep_token": "</s>", | |
| "special_tokens_map_file": null, | |
| "tokenizer_class": "BartTokenizer", | |
| "trim_offsets": true, | |
| "unk_token": "<unk>" | |
| } | |