·
AI & ML interests
None yet
Organizations
Lux0926/Qwen1.5-32B-SFT-CGPO
Lux0926/DeepSeekMath-Base-7B-SFT-CGPO
Lux0926/Qwen2-7B-SFT-CGPO
Lux0926/MetaMath-Llama-8B-CGPO
Lux0926/MetaMath-Mistral-7B-CGPO
Lux0926/MetaMath-Mistral-7B-Step-DPO
7B • Updated Lux0926/MetaMath-Llama-8B-Step-DPO
8B • Updated Lux0926/Deepseek-Coder-7B-Instruct-v1.5-CGPO
7B • Updated Lux0926/ASPRM-Training-Evaluation-Environment
Updated
Lux0926/ASPRM-MATHCODE-DeepSeek
7B • Updated • 2
Lux0926/ASPRM-MATHCODE-Mistral
7B • Updated • 2
7B • Updated • 2
8B • Updated • 5
• 1
7B • Updated • 8
• 1
Lux0926/metamath_mistral_7b
Updated
Lux0926/MetaMath-LLaMA-8B
8B • Updated • 3
• 1