This model applies the LLM2Vec method to Meta's Llama 3 8B Instruct model with MNTP-supervised training. It transforms the LLM into a powerful text embedding model optimized for sentence similarity and information retrieval tasks. Developed by the McGill NLP Group, it is available for use with the Transformers library.
LLM2Vec Meta Llama 3 8B Instruct Mntp Supervised is a Foundation models & chat project. It focuses on converting decoder-only LLMs into high-quality text embedding models for semantic search and retrieval. It is built as an open-source project for developers. The project is open source (Open Source). It runs on the web and API.
It is developed by McGill NLP Group (Canada), and it first shipped in 2024. Key capabilities include text embeddings, sentence similarity, and information retrieval.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do