Summarization
Transformers
TensorBoard
Safetensors
English
pegasus
text2text-generation
fine-tuned
google-pegasus-xsum
ccdv/govreport-summarization
Instructions to use nppiech/a-text-summarizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nppiech/a-text-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="nppiech/a-text-summarizer")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("nppiech/a-text-summarizer") model = AutoModelForSeq2SeqLM.from_pretrained("nppiech/a-text-summarizer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from nppiech/a-text-summarizer: direct link, hf CLI and curl.
- Browser
- Download file 254 Bytes
-
https://huggingface.co/nppiech/a-text-summarizer/resolve/main/generation_config.json
- Command line
-
hf download hf://nppiech/a-text-summarizer/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/nppiech/a-text-summarizer/resolve/main/generation_config.json
254 Bytes
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 0, | |
| "decoder_start_token_id": 0, | |
| "eos_token_id": 1, | |
| "forced_eos_token_id": 1, | |
| "length_penalty": 0.6, | |
| "max_length": 64, | |
| "num_beams": 8, | |
| "pad_token_id": 0, | |
| "transformers_version": "4.55.0" | |
| } | |