LLM2Vec Meta Llama 3 8B Instruct MNTP
JSON →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.
Specs
context window 8K tokens
max output 8K tokens
input price $0.15 / 1M tokens
output price $0.15 / 1M tokens
Capabilities
open-weights
Dates
releasedJun 2024