Matteo Cercola

matCercola18 's models 96

Sort:  Recently updated

matCercola18/Qwen2.5-7B-GRPO-full

Text Generation • 333k • Updated Feb 23 • 6

matCercola18/Qwen2.5-7B-GRPO-faith-v0

Text Generation • 333k • Updated Feb 23 • 6

matCercola18/Qwen2.5-7B-GRPO-corr-v0

Text Generation • 333k • Updated Feb 21 • 5

matCercola18/Qwen2.5-7B-GRPO-all-v0

Text Generation • 8B • Updated Feb 21 • 7

matCercola18/reward_model_dahos

Text Classification • 44.7M • Updated Jul 16, 2025 • 4

matCercola18/reward_model_dahos_lora

Text Classification • 44.7M • Updated Jul 10, 2025 • 3