cgcg's picture

1 7

cgcg

cg666

AI & ML interests

None yet

Organizations

None yet

cg666 's models 140

cg666/Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-ghpo-cold10-3Dhint-prompt1-dp

Updated Apr 29, 2025

cg666/Qwen-2.5-Base-7B-gen8-math3to5-ghpo-cold30-3Dhint-prompt1-cosine

Updated Apr 29, 2025

cg666/Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-ghpo-cold30-3Dhint-prompt1-dp

Updated Apr 29, 2025

cg666/Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-grpo-prompt1-dp

Updated Apr 29, 2025

cg666/Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-ghpo-cold30-3Dhint-prompt1

Text Generation • 8B • Updated Apr 28, 2025 • 2

cg666/Qwen-2.5-Base-7B-gen8-math3to5-ghpo-cold0-3Dhint-prompt1-epoch3

Text Generation • 8B • Updated Apr 27, 2025 • 2

cg666/Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-ghpo-cold0-3Dhint-prompt0

Text Generation • 8B • Updated Apr 26, 2025 • 1

cg666/Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-ghpo-cold0-3Dhint-prompt1

Text Generation • 8B • Updated Apr 26, 2025 • 2

cg666/Qwen2.5-Math-7B-gen8-math3to5_olympiads_aime-ghpo-cold-Dhint35-epoch1

8B • Updated Apr 25, 2025 • 1

cg666/Qwen2.5-Math-7B-gen8-math3to5_olympiads_aime-grpo-epoch1

Text Generation • 8B • Updated Apr 24, 2025 • 2

cg666/Qwen-2.5-Base-7B-gen8-math3to5-ghpo-cold-Dhint5-7-epoch5

8B • Updated Apr 24, 2025 • 1

cg666/Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-ghpo-cold-Dhint-epoch5

8B • Updated Apr 21, 2025 • 1

cg666/Qwen-2.5-Base-7B-gen8-math3to5-ghpo-cold-Dhint-epoch5

8B • Updated Apr 19, 2025 • 1

cg666/Qwen-2.5-Base-7B-gen8-math3to5-100-ghpo-hint0.5-epoch2-test

Updated Apr 17, 2025

cg666/Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-ghpo-hint0.5-epoch2-save20

8B • Updated Apr 16, 2025 • 1

cg666/openr1-Qwen-2.5-Base-7B-grpo-epoch2-save2-debug

Updated Apr 16, 2025

cg666/Qwen-2.5-Base-7B-gen8-math3to5-ghpo-hint0.5-epoch2-save10

8B • Updated Apr 16, 2025 • 1

cg666/openr1-Qwen-2.5-Base-7B-grpo-epoch2-save2

Updated Apr 15, 2025

cg666/openr1-Qwen-2.5-Base-7B-grpo-epoch2-save

Updated Apr 15, 2025

cg666/openr1-Qwen-2.5-Base-7B-gen8-math3to5-grpo-epoch3-test

Updated Apr 15, 2025

cg666/openr1-Qwen-2.5-Base-7B-gen8-math3to5-grpo-epoch3

Text Generation • 8B • Updated Apr 14, 2025 • 3

cg666/openr1-Qwen-2.5-Base-7B-gen8-math3to5-ghpo-hint0.5-epoch3-v3

Updated Apr 14, 2025

cg666/openr1-Qwen-2.5-Base-7B-gen8-math3to5-ghpo-hint0.5-epoch3-v2

Updated Apr 14, 2025

cg666/openr1-Qwen-2.5-Base-7B-gen8-math3to5-ghpo-hint0.5-epoch3-new

Updated Apr 14, 2025

cg666/openr1-Qwen-2.5-Base-7B-gen8-math3to5-ghpo-hint0.5-epoch3

Updated Apr 14, 2025

cg666/openr1-Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-hint0.7-epoch3

8B • Updated Apr 13, 2025 • 1

cg666/openr1-Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-ghpo-epoch3

Text Generation • 8B • Updated Apr 13, 2025 • 2

cg666/openr1-Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-grpo-epoch3

Text Generation • 8B • Updated Apr 12, 2025 • 1

cg666/openr1-Qwen-2.5-Base-3B-gen8-scale-NuminaMath-TIR-100-ghpo-beta0-epoch2-test

Updated Apr 11, 2025

cg666/openr1-Qwen-2.5-Base-3B-gen8-scale-NuminaMath-TIR-100-grpo-beta0-epoch2-2

Updated Apr 11, 2025