tarekziade/t5-small-booksum-sft-3-3
By tarekziade · ↓ 2 · ♥ 0 · Updated 2024-01-29
What's in this repo
This page lists the files in tarekziade/t5-small-booksum-sft-3-3, including decoder_model.onnx, decoder_model_merged.onnx, decoder_model_merged_quantized.onnx and more.
- 8 ONNX models (.onnx files)
- 19 files, including 8 .onnx, 7 .json, 1 .md, 1 .safetensors, 1 .model
- Last updated 2024-01-29
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/decoder_model.onnx | — | Download |
| onnx/decoder_model_merged.onnx | — | Download |
| onnx/decoder_model_merged_quantized.onnx | — | Download |
| onnx/decoder_model_quantized.onnx | — | Download |
| onnx/decoder_with_past_model.onnx | — | Download |
| onnx/decoder_with_past_model_quantized.onnx | — | Download |
| onnx/encoder_model.onnx | — | Download |
| onnx/encoder_model_quantized.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 is a Shrinked and Fine-tuned version of https://huggingface.co/cnicu/t5-small-booksum
See https://ziade.org/2024/01/27/compressing-t5-models-for-summarization/ for the rationale.
Accuracy after shrinking:
rouge-1 Accuracy:
- F1 Accuracy: 95.99%
- Precision Accuracy: 85.37%
- Recall Accuracy: 95.73%
rouge-2 Accuracy:
- F1 Accuracy: 99.54%
- Precision Accuracy: 97.14%
- Recall Accuracy: 99.54%
rouge-l Accuracy:
- F1 Accuracy: 96.76%
- Precision Accuracy: 84.41%
- Recall Accuracy: 96.36%
Model info
Created: 2024-01-29
Updated: 2024-01-29
View on Hugging FaceFiles (19)
Related models
More from tarekziade
More models
No task type declared.