LLM2Vec Meta Llama 3 8B Instruct MNTP

JSON →
mcgill-nlp embedding
text

An 8-billion parameter embedding model from McGill NLP, converting Meta's Llama 3 Instruct into a text embedding model via masked next token prediction.

context window 8K tokens
max output 8K tokens
input price $0.15 / 1M tokens
output price $0.15 / 1M tokens
open-weights
releasedJun 2024