AmberYifan/qwen2.5-3b_aime_grpo_structure_only_step45
3B • Updated • 3
Yifan Wang
AmberYifan
AI & ML interests
None yet
Recent Activity
updated a model 2 months ago
AmberYifan/capsd-final-retrain-marin-8b-base-code_less_b8000_s0 published a model 2 months ago
AmberYifan/capsd-final-retrain-marin-8b-base-code_less_b8000_s0 updated a model 2 months ago
AmberYifan/capsd-marin-8b-base-n80000-opc-r144-marin-8b-base-code_cap_b8000_s0Organizations
AmberYifan/qwen2.5-3b_aime_grpo_acc_structure_step45
3B • Updated • 3
AmberYifan/qwen2.5-3b_aime_grpo_acc_only_step45
3B • Updated • 6
AmberYifan/phi4-mini-reasoning_aime_grpo_structure_only_step45
4B • Updated • 3
AmberYifan/ministral-3-3b-reasoning-2512_openrubrics_v2_ppo_structure_only_step60
4B • Updated • 3
AmberYifan/ministral-3-3b-reasoning-2512_openrubrics_v2_ppo_reward_model_step60
4B • Updated • 6
AmberYifan/ministral-3-3b-reasoning-2512_openrubrics_v2_grpo_reward_model_step60
4B • Updated • 6
AmberYifan/ministral-3-3b-reasoning-2512_aime_ppo_structure_only_step45
4B • Updated • 4
AmberYifan/ministral-3-3b-reasoning-2512_aime_ppo_acc_only_step45
4B • Updated • 4
AmberYifan/ministral-3-3B-reasoning-2512_openrubrics_v2_grpo_structure_only_step60
4B • Updated • 2
AmberYifan/ministral-3-3B-reasoning-2512_aime_ttrl_step45
4B • Updated • 3
AmberYifan/ministral-3-3B-reasoning-2512_aime_grpo_structure_only_step45
4B • Updated • 4
AmberYifan/ministral-3-3B-reasoning-2512_aime_grpo_acc_only_step45
4B • Updated • 3
AmberYifan/llama3-8b-full-pretrain-low-len-1m-en-sft
Text Generation • 8B • Updated • 12
AmberYifan/llama3-8b-full-pretrain-high-len-1m-en-sft
Text Generation • 8B • Updated • 6
AmberYifan/llama3-8b-full-pretrain-high-len-1m-en
Text Generation • 8B • Updated • 13
AmberYifan/llama3-8b-full-pretrain-low-len-1m-en
Text Generation • 8B • Updated • 10
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-mix-low-tweet-1m-en-gpt-sft
Text Generation • 0.5B • Updated • 7
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-mix-mid-tweet-1m-en-gpt-sft
Text Generation • 0.5B • Updated • 13
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-mix-high-tweet-1m-en-gpt-sft
Text Generation • 0.5B • Updated • 4
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-junk-tweet-1m-en-gpt-sft
Text Generation • 0.5B • Updated • 10
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-control-tweet-1m-en-gpt-sft
Text Generation • 0.5B • Updated • 12
AmberYifan/qwen2.5-7b-instruct-full-pretrain-mix-low-tweet-1m-en-gpt-sft
Text Generation • 8B • Updated • 12
AmberYifan/qwen2.5-7b-instruct-full-pretrain-mix-mid-tweet-1m-en-gpt-sft
Text Generation • 8B • Updated • 6
AmberYifan/qwen2.5-7b-instruct-full-pretrain-mix-high-tweet-1m-en-gpt-sft
Text Generation • 8B • Updated • 11
AmberYifan/qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-gpt-sft
Text Generation • 8B • Updated • 18
AmberYifan/qwen2.5-7b-instruct-full-pretrain-control-tweet-1m-en-gpt-sft
Text Generation • 8B • Updated • 16
AmberYifan/qwen2.5-7b-instruct-full-pretrain-control-tweet-1m-en-gpt
Text Generation • 8B • Updated • 26
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-mix-low-tweet-1m-en-sft
Text Generation • 0.5B • Updated • 8
AmberYifan/qwen2.5-0.5b-instruct-full-pretrain-mix-mid-tweet-1m-en-sft
Text Generation • 0.5B • Updated • 7