shorecode/t5-efficient-tiny-summarizer-general-purpose-v3
By shorecode · ↓ 4 · ♥ 1 · Updated 2025-11-05
What's in this repo
This page lists the files in shorecode/t5-efficient-tiny-summarizer-general-purpose-v3, including decoder_model.onnx, decoder_with_past_model.onnx, encoder_model.onnx.
- 3 ONNX models (.onnx files)
- 27 files, including 13 .json, 4 .bin, 3 .onnx, 2 .pt, 1 .md, 1 .png
- Last updated 2025-11-05
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/decoder_model.onnx | — | Download |
| onnx/decoder_with_past_model.onnx | — | Download |
| onnx/encoder_model.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
This model was built to shorten text that is injected into LLM prompts to reduce API calling costs
Very high compression (7x+) meaning the text is 7 times smaller when sent to your LLM provider! Recommended kwargs:
- num_beams=2 || 3
- no_repeat_ngram_size=2
- min_length=20
- max_new_tokens=500 || as high as you can tolerate, 4x500 = 2000 characters. anything after 2000 is clipped
https://api.wandb.ai/links/shorecode-shorecode-llc/6udfudmr
Model info
Created: 2025-10-31
Updated: 2025-11-05
View on Hugging FaceFiles (27)
Related models
More from shorecode
More models
No task type declared.