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.
More from Models
- GPT 6.1 'Astra' Rumors Swirl as OpenAI's Release Pace Stuns Observers — bindureddy · 2026-09-25
- GPT-6 models duel in DOOM: Astra wins 82.5% of 120 agent matches — OpenAIDevs · 2026-09-25
- User warns Sol-6 high mode hallucinates finished work, forcing constant rework — Babayaga1664 · 2026-09-25
- Alexandr Wang amplifies Muse skepticism post calling the model 'underwhelming and useless' — maheen_sohail · 2026-09-25
- The AI Meme: Wait Until Your Project Is 78% Done, Then They Nerf the Model — BLUECOW009 · 2026-09-25
- Open Weights Beat Black-Box APIs on Security: Sandboxing Is an Engineering Problem — ypatil125 · 2026-09-25