termgrade-gemma4-31b-merged
Part of TermGrade: graded environments and trajectories for terminal agents. Read the blog post. 46.1 on Terminal-Bench 2.1...
Part of TermGrade: graded environments and trajectories for terminal agents. Read the blog post. 46.1 on Terminal-Bench 2.1...
Part of TermGrade: graded environments and trajectories for terminal agents. Read the blog post. 46.1 on Terminal-Bench 2.1...
A full fine-tune of LiquidAI/LFM2.5-2.6B for agentic data-analysis tasks, trained with asynchronous GRPO (TRL Async GRPO) using OpenCode,...
Qwen3-4B Calendar Agent RLVR는 한국어 일정 관리 도구를 호출하는 4B 파라미터 병합 모델입니다. Calendar 도구의 실행 궤적과 최종...
This is the flagship release of CantoneseLLM v2. It is a 30.5B-parameter mixture-of-experts model (3.3B activated) based on...
An 8B dense model based on Qwen3-8B that reasons and answers in Hong Kong Cantonese. It is the...
This is a Natural Language Autoencoder (Anthropic, 2026) trained for Qwen/Qwen3.6-27B on layer-42 residual-stream activations using easyNLA. This...
MIST-Mini-8B-Thinking is the reasoning version of MIST-Mini-8B by olaverse. Trained with 4 phases of GRPO (Group Relative Policy...
Atomight-V2.1-0.5B-Inference — это ультракомпактная, ориентированная на рассуждения причинно-следственная языковая модель, разработанная в рамках экосистемы Atomight. Построенная на основе...
LoRA adapter fine-tuned from Qwen/Qwen3-8B for collaborative creative writing (poems, short stories) with the DiscoverLLM training framework (paper...