shorecode/t5-efficient-tiny-summarizer-general-purpose-v3

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
• —norepeatngram_size=2
• —min_length=20
• —maxnewtokens=500 || as high as you can tolerate, 4x500 = 2000 characters. anything after 2000 is clipped <Gallery />

https://api.wandb.ai/links/shorecode-shorecode-llc/6udfudmr