Contrastive-LM releases CLM-v0.1-8B, a Qwen3-8B-based reranker trending on Hugging Face

Contrastive-LM · hf · 2026-09-25

Contrastive-LM has released CLM-v0.1-8B, a text-ranking model fine-tuned from Qwen3-8B using contrastive learning, positioned as a verifier/reranker for agent workflows. It ships under the Apache-2.0 license and is currently trending on Hugging Face, offering an open-source option for reranking and candidate verification in agent pipelines.

Original post →

More from Models

Models channel →