grigio@alien.topB to LocalLLaMA@poweruser.forumEnglish · 1 year agoIs there a 7B model capable to extract keywords from a text and return them as an array?message-squaremessage-square16fedilinkarrow-up11arrow-down10file-text
arrow-up11arrow-down1message-squareIs there a 7B model capable to extract keywords from a text and return them as an array?grigio@alien.topB to LocalLLaMA@poweruser.forumEnglish · 1 year agomessage-square16fedilinkfile-text
Prompt like: Extract the company names from the texts below and return as an array – [“Google”, “Meta”, “Microsoft”]
minus-squareBrainSlugs83@alien.topcakeBlinkfedilinkEnglisharrow-up1·1 year agoWhy do you need an LLM for this? Just use any NER model. It will be blazing fast and run locally.
minus-squareLPN64@alien.topBlinkfedilinkEnglisharrow-up1·1 year agoBecause let’s say you train your bert model to do this, you’ll have a specific limited class trained on a specific type of document. It will work on wikipedia articles but not on transcripts from your local police station. Using a llm will allow it to inherit from the wide knowledge of the llm.
Why do you need an LLM for this? Just use any NER model. It will be blazing fast and run locally.
Because let’s say you train your bert model to do this, you’ll have a specific limited class trained on a specific type of document.
It will work on wikipedia articles but not on transcripts from your local police station.
Using a llm will allow it to inherit from the wide knowledge of the llm.