search

McGill-NLP / llm2vec

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
https://mcgill-nlp.github.io/llm2vec/
MIT License
816 stars 59 forks source link

gemma model #102

Closed vaibhavad closed 2 weeks ago

kabachuha commented 1 week ago

Hi! Will a pretrained llm2vec checkpoint be released for Gemma or this PR is just a recipe for its training? (maybe its license is not very open)

vaibhavad commented 1 week ago

Hi @kabachuha, this PR is just a recipe for its training. The goal is to provide support for many models and make it easier for the community to train their own LLM2Vec models.

kabachuha commented 1 week ago

Thanks anyway :)