⬢github Python · 1.6K ★ +123 since we first saw it · pushed 2 d ago · Apache-2.0
Contrastive-LM/CLM
CLM is a Python library serving Contrastive Language Model-8B, a model trained contrastively to connect states and actions for fast 'System One' decision-making. It exposes a TypeSafe-compatible API for scoring states, asking typed questions (boolean/choice/score), and ranking candidate answers. A vLLM embedding server plus a small 75 MB reference head make serving lightweight, with cached state/action embeddings for low latency.
Why now: It just launched as a highly starred new repo (v0.1, ~1.5k stars within a day), claiming performance on par with a rival 'Jev' at up to 9× lower latency and new SOTA verifier results on Terminal-Bench 2.1 and DeepSWE, plus an open invitation to benchmark it.
Who it is for: ML engineers and agent builders who want a fast, lightweight model to score states, verify agent outputs, or rank candidates in their own pipelines.
Stars over our 45 snapshots: 1.5K to 1.6K, since 9 h ago.
Where people talked about it
- ⬢github new repos, most starred 5 min ago
- ⬢github new repos, most starred 3 h ago
API: https://socialmediatrends-api.osmike.com/v1/repos/Contrastive-LM/CLM