cgcg

cg666 's models 140

Sort:  Recently updated

cg666/Qwen2.5-3B-Instruct-grpo-MATHDATA-E1

Text Generation • 3B • Updated Mar 7, 2025 • 1

cg666/Qwen-2.5-7B-Instruct-Simple-RL-test

Updated Mar 7, 2025

cg666/Qwen-2.5-7B-Instruct-Simple-RL

Updated Mar 7, 2025

cg666/Qwen-2.5-7B-Simple-RL

Text Generation • 8B • Updated Mar 6, 2025 • 3 •

cg666/Qwen2.5-3B-Instruct-grpo-E6-D100-L4096-lr5e7

Text Generation • 3B • Updated Mar 6, 2025 • 2

cg666/Qwen2.5-3B-Instruct-grpo-E6-D8000-L4096-lr5e7

Text Generation • 3B • Updated Mar 6, 2025 • 3

cg666/Qwen2.5-3B-Instruct-grpo-E6-D8000-L4096

Text Generation • 3B • Updated Mar 5, 2025 • 2

cg666/Qwen2.5-3B-Instruct-grpo-E6-D8000

Updated Mar 4, 2025

cg666/OLMoE-1B-7B-0125-Instruct-grpo-E6-D8000-L4096

Text Generation • 7B • Updated Mar 4, 2025 • 1

cg666/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

Updated Mar 3, 2025

cg666/OLMoE-1B-7B-0125-Instruct-grpo-test

Updated Mar 3, 2025

cg666/OLMoE-1B-7B-0125-Instruct-grpo-E6-D8000

7B • Updated Mar 3, 2025 • 1

cg666/OLMoE-1B-7B-0125-Instruct-grpo-E8-D8000

Text Generation • 7B • Updated Mar 1, 2025 • 2

cg666/OLMoE-1B-7B-0125-Instruct-grpo-E6-D100

Text Generation • 7B • Updated Feb 28, 2025 • 2

cg666/OLMoE-1B-7B-0125-Instruct-grpo-E5-D8000

Updated Feb 25, 2025

cg666/OLMoE-1B-7B-0125-Instruct-grpo

Text Generation • 7B • Updated Feb 25, 2025 • 3 • 1

cg666/Qwen2.5-3B-Instruct-grpo

Text Generation • 3B • Updated Feb 19, 2025 • 1

cg666/OLMoE-1B-7B-0125-grpo

Updated Feb 18, 2025

cg666/deepseek-v2-lite-chat-16B-grpo

Updated Feb 13, 2025

cg666/LLaMA_factory

Updated Dec 4, 2024