A surprisingly effective way to predict token importance in LLM prompts
We explored a novel method to gauge the significance of tokens in prompts given to large language models, without needing direct model access.
Reactions (1)
Similar products
by description similarity
Steerling-8B
guidelabs.aia language model that can explain any token it generates
A ~9M parameter LLM that talks like a small fish.
Automatic prompt optimizer for LLMs
promptperfect.jina.aiA proof-of-concept language learning app that uses LLMs to generate definitions of unknown words using only previously mastered vocabulary.
PrePrompt
preprompt.orgrewrites vague prompts before they reach the LLM