Yifan Wang's picture

1 3 1

Yifan Wang

AmberYifan

·

AI & ML interests

None yet

Recent Activity

published a model 2 days ago

AmberYifan/Qwen3-4B-MATH-GRPO-len-control-tuned-test

published a model 3 days ago

AmberYifan/Qwen3-4B-MATH-GRPO-len-control-tuned

published a model 4 days ago

AmberYifan/Qwen3-4B-OpenR1Math-MARL-structure-v2

View all activity

Organizations

AmberYifan 's models 639

AmberYifan/Qwen3-4B-MATH-GRPO-len-control-tuned-test

Updated 2 days ago

AmberYifan/Qwen3-4B-MATH-GRPO-len-control-tuned

Updated 3 days ago

AmberYifan/Qwen3-4B-OpenR1Math-MARL-structure-v2

Updated 4 days ago

AmberYifan/Qwen3-4B-Polaris-MARL-structure-v2

Updated 4 days ago

AmberYifan/Qwen3-4B-MATH-MARL-structure-v2

Updated 5 days ago

AmberYifan/Qwen3-1.7B-MATH-MARL-structure

Updated 5 days ago

AmberYifan/Qwen3-1.7B-MATH-MARL-tuned

Updated 8 days ago

AmberYifan/Qwen3-4B-MATH-MARL-tuned

Updated 9 days ago

AmberYifan/Qwen3-4B-MATH-GRPO-tuned

Updated 10 days ago

AmberYifan/Qwen3-4B-MATH-MARL-structure-loop-penalty-v2-32

Updated 18 days ago

AmberYifan/Qwen3-4B-OpenR1Math-MARL-structure-loop-penalty-v2

Updated 18 days ago

AmberYifan/Phi-4-mini-reasoning-MATH-MARL-structure-loop-penalty-v2

Updated 18 days ago

AmberYifan/Qwen3-4B-MATH-MARL-structure-loop-penalty-v2

4B • Updated 20 days ago • 33

AmberYifan/Qwen3-4B-MATH-MARL-structure-loop-penalty

Text Generation • 4B • Updated 25 days ago • 97

AmberYifan/Qwen3-4B-MATH-MARL-structure

Text Generation • 4B • Updated Sep 28 • 5 • 1

AmberYifan/Qwen3-4B-MATH-GRPO-len-control

Text Generation • 4B • Updated Sep 28 • 7

AmberYifan/Qwen3-4B-MATH-GRPO-acc

Text Generation • 4B • Updated Sep 28 • 6

AmberYifan/llama3-8b-full-pretrain-low-pop-1m-en-sft

Text Generation • 8B • Updated Sep 24 • 2

AmberYifan/llama3-8b-full-pretrain-low-len-1m-en-sft

Text Generation • 8B • Updated Sep 24 • 2

AmberYifan/llama3-8b-full-pretrain-low-pop-1m-en

Text Generation • 8B • Updated Sep 24 • 2

AmberYifan/llama3-8b-full-pretrain-high-pop-1m-en-sft

Text Generation • 8B • Updated Sep 24 • 3

AmberYifan/llama3-8b-full-pretrain-high-len-1m-en-sft

Text Generation • 8B • Updated Sep 24 • 3

AmberYifan/llama3-8b-full-pretrain-high-len-1m-en

Text Generation • 8B • Updated Sep 24 • 2

AmberYifan/llama3-8b-full-pretrain-low-len-1m-en

Text Generation • 8B • Updated Sep 24 • 3

AmberYifan/llama3-8b-full-pretrain-high-pop-1m-en

Text Generation • 8B • Updated Sep 24 • 2

AmberYifan/qwen2.5-0.5b-instruct-alpaca-sft

Text Generation • 0.5B • Updated Sep 23 • 2

AmberYifan/qwen3-4b-thinking-alpaca-sft

Text Generation • 4B • Updated Sep 23 • 1

AmberYifan/qwen2.5-7b-instruct-alpaca-sft

Text Generation • 8B • Updated Sep 23 • 4 • 1

AmberYifan/llama3-8b-instruct-alpaca-sft

Text Generation • 8B • Updated Sep 23 • 1

AmberYifan/llama3-8b-full-pretrain-junk-tweet-1m-en-wash-control-1.2m-sft

Text Generation • 8B • Updated Sep 22 • 1