CLM vs laya
Contrastive Language Models: CLM-8B, an open System-1 decision model scoring states against actions — typed choice/score/yes-no answers on a TypeSafe-compatible API, up to 9x faster than Jev. — versus — Non-autoregressive decision engine: typed choice, score and yes/no answers over text in one forward pass (~33 ms), 100+ languages, calibrated probabilities, a router picking the checkpoint.
Both answer typed choice/score/yes-no questions in one pass with calibrated probabilities; Laya is a non-autoregressive multilingual engine, CLM a contrastive state-action ranker with cached embeddings.
| CLM | laya | |
|---|---|---|
| Stars | 3.0k | 32k |
| Forks | 256 | 2.8k |
| Language | Python | Python |
| License | Apache-2.0 | Apache-2.0 |
| Last activity | 6 days ago | 4 days ago |
| Topics | decision-models, local | decision-models, local |
| Curated connections | 5 | 6 |
CLM — the curator's take
Use it when an agent must pick among many candidates fast — next action, tool, best-of-N verifier — and you want calibrated probabilities on your own GPU; cached state/action embeddings are why it beats Jev on latency. Not for anything generative: it ranks, never writes. Needs a Qwen3-8B encoder under vLLM plus the head, and states past 2,048 tokens are truncated unless you raise both limits.
laya — the curator's take
Use laya where you now spend an LLM call on a classification: routing a ticket, scoring urgency, a yes/no guard. Typed questions in, calibrated probabilities out, in one pass of about 33 ms, in 100+ languages, with pip install and extras for LangGraph, LlamaIndex, CrewAI, MCP and an HTTP server. The probabilities are the point: you can threshold them. Mind the limits it publishes itself: the multilingual checkpoint cuts at 1,024 tokens unless you pass max_len=8192, and past about 4,000 tokens its own long-document bench drops to 8 to 17 correct of 20. It decides; it does not explain or extract, so free-form answers still need an LLM. Two weeks old despite the star count: pin the version.