Bespoke Miniature NB

Software / App

A 7B model from Bespoke Labs for Natural Language Inference (NLI) task, which successfully beat its 45B teacher model (Llama 2/3 45B) through data curation.

Mentioned in 1 video

Videos Mentioning Bespoke Miniature NB

The Unreasonable Effectiveness of Reasoning Distillation: using DeepSeek R1 to beat OpenAI o1

The Unreasonable Effectiveness of Reasoning Distillation: using DeepSeek R1 to beat OpenAI o1

Latent Space

A 7B model from Bespoke Labs for Natural Language Inference (NLI) task, which successfully beat its 45B teacher model (Llama 2/3 45B) through data curation.