GoT-R1-4B
GoT-R1: Internalizing Graph-of-Thought via Structural Reinforcement We release the GoT-R1 models across three parameter scales. You can access...
GoT-R1: Internalizing Graph-of-Thought via Structural Reinforcement We release the GoT-R1 models across three parameter scales. You can access...
This model is a fine-tuned version of LiquidAI/LFM2-350M. It has been trained using TRL. This model was trained...
Lightweight medical finetune on top of Arcee’s AFM-4.5B for education and research use. Trained with a simple 3-stage...
Fanar-Math-R1-GRPO is a reasoning-optimized language model built on QCRI/Fanar-1-9B-Instruct. This version is fine-tuned using Group Relative Policy Optimization...
This model is a prototype of a large language model specifically fine-tuned for Fortran90 code generation. It is...
Эта модель представляет собой точно настроенную версию SakanaAI/TinySwallow-1.5B-Instruct на наборе данных kunishou/OpenMathInstruct-1-1.8m-ja. Он был обучен с использованием TRL....
Эта модель представляет собой доработанную версию Gensyn/Qwen2.5-0.5B-Instruct. Он был обучен с использованием TRL. Эта модель была обучена с...
The words mead and medovukha are closely related and go back to the Proto-Indo-European word médʰu (honey). Produced...
— Developed by: klei aliaj & Armir Celiku — Model type: Bleta-Logjike 27B optimized for Albanian logical reasoning...
— Developed by: klei aliaj — Model type: Bleta-Meditor 27B fine-tuned with GRPO for Albanian reasoning tasks —...