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

Prompt
Model training

Safetensors

Model size

15.6M params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for shorecode/t5-efficient-tiny-summarizer-general-purpose-v3

Base model

Quantized

(2)

this model

f1 Score on shorecode/summary-collection-60k-rows
self-reported

0.290
Faithfullness (facebook/bart-large-cnn) on shorecode/summary-collection-60k-rows
self-reported

1.710
Summarization Compression on shorecode/summary-collection-60k-rows
self-reported

7.520
Summarization Coverage on shorecode/summary-collection-60k-rows
self-reported

0.960
Summarization Density on shorecode/summary-collection-60k-rows
self-reported

8.680
rougeL precision on shorecode/summary-collection-60k-rows
self-reported

0.590
rougeL recall on shorecode/summary-collection-60k-rows
self-reported

0.310
rougeL fmeasure on shorecode/summary-collection-60k-rows
self-reported

0.410
rouge1 precision on shorecode/summary-collection-60k-rows
self-reported

0.630
rouge1 recall on shorecode/summary-collection-60k-rows
self-reported

0.330