bleta-logjike-27b
— Developed by: klei aliaj & Armir Celiku — Model type: Bleta-Logjike 27B optimized for Albanian logical reasoning...
Метка: gsm8k
prem-1B-grpo
This model was fine-tuned using GRPO (Generative Reward-Powered Optimization), a reinforcement learning technique that optimizes language models using...
Monostep-v1
MONOSTEP is a small (~16.6M parameter) experimental research model trained on GSM8K. Instead of predicting one token at...
qwen3-1.7b-gsm8k-sft
This model is a fine-tuned version of Qwen/Qwen3-1.7B optimized for mathematical reasoning on the GSM8K benchmark. For deployment...
Qwen2.5-Math-Coder-Distill-Phi-2-4.4K-MixMathCode
Модель была обучена на объединенном наборе данных задач программирования на Python (из MBPP и opc-sft-stage2) и задач по...