ModelF2LLM-v2-8B
F2LLM-v2-8B
An 8-billion-parameter large embedding model in the F2LLM-v2 series, commonly used as a teacher model for relational knowledge distillation of retrieval models.
Timeline (last 90 days)
Oct 26
F2LLM-v2 is a family of multilingual embedding models, in which F2LLM-v2-0.6B is a comparison baseline of the same scale and F2LLM-v2-8B serves as the teacher model for knowledge distillation.
Unverified50%