⬢github Python · 1.8K ★ +3 since we first saw it · pushed 2 d ago
bespokelabsai/nimble
Local typed decisions, contrastive data curation, and model evaluation.
Bespoke Nimble is an open recipe for building a fast, typed classification model. Given text and a schema of questions (multiple-choice or true/false), Bespoke-Nimble-9B returns each answer with per-choice probabilities in a single step, no chain-of-thought reasoning. The repo covers contrastive data curation, LoRA fine-tuning of Qwen3.5-9B, and serving, runnable on Apple Silicon or NVIDIA GPUs.
Why now: It's trending as a new, highly starred open replication of TypeSafe's Jev System One model, with a recently released 9B checkpoint, public training data, and a shared benchmark suite.
Who it is for: ML engineers and researchers who want fast, schema-driven classification decisions with calibrated probabilities and an open training recipe.
Stars over our 15 snapshots: 1.8K to 1.8K, since 1 h ago.
Where people talked about it
- ⬢github new repos, most starred 4 min ago
API: https://socialmediatrends-api.osmike.com/v1/repos/bespokelabsai/nimble