hzy/WideSeek-8B-RL
8B • Updated • 1
Ziyang
hzy
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios upvoted a paper about 2 months ago
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker AgentsOrganizations
None yet
hzy/WideSeek-8B-SFT-RL
8B • Updated • 1 • 1
hzy/WideSeek-8B-SFT
308k • Updated • 1
hzy/VideoSimpleQA
Updated
hzy/next-video
Updated
hzy/ikea-qwen2.5-3b-it
3B • Updated • 8 • 1
hzy/ikea-qwen2.5-3b
3B • Updated • 5
hzy/ikea-qwen2.5-7b
8B • Updated • 2
hzy/ikea-qwen2.5-7b-it
8B • Updated • 3 • 1
hzy/qwen1.5b-math-base-3-to-5-grpo_std_on-mi300x-3000-drgrpo-len-with-entropy-loss-step-980
2B • Updated • 5
hzy/qwen1.5b-math-base-3-to-5-grpo-step-280
2B • Updated • 1
hzy/qwen1.5b-math-grpo_std_on_grpo_std_on_grpo_mi300-step-280
2B • Updated • 2
hzy/qwen1.5b-math-grpo_std_on_grpo_std_on-20240401-step-240
2B • Updated • 2
hzy/qwen2.5-3b-it-fb-sft-with-tag
Text Generation • 3B • Updated • 4
hzy/qwen1.5b-math-grpo_std_on_grpo-20240401-step-280
2B • Updated • 1
hzy/qwen2.5-3b-it-fb-sft-1epoch
Text Generation • 3B • Updated • 1
hzy/qwen1.5b-math-grpo_std_on-20240330-step-290
2B • Updated • 1
hzy/qwen1.5b-math-grpo_std_on-20240330-step-280
2B • Updated • 1
hzy/qwen1.5b-math-grpo-20240330-step-260
2B • Updated • 1
hzy/qwen1.5b-math-grpo-20240330-step-200
2B • Updated • 1
hzy/qwen2.5_1.5b-math-stage2-naive-grpo_std_on-with-large-rollout_with_df_20250328-step-180
2B • Updated • 2
hzy/qwen2.5_1.5b-math-naive-stage2-grpo_std_on-with-large-rollout-step-120
2B • Updated • 4
hzy/qwen2.5_1.5b-math-short-0-long-1-restricted-overlong-1024-0.5-len-reward-step-640
2B • Updated • 2
hzy/verl-grpo-math-qwen2.5-1.5b-short-0-long-1-restricted-overlong-1024-step-140
2B • Updated • 1
hzy/verl-grpo-math-qwen2.5-1.5b-short-0-long-1-restricted-overlong-1024-step-120
2B • Updated • 2
hzy/verl-grpo-math-qwen2.5-1.5b-short-0-long-1-restricted-overlong-1024-step-400
2B • Updated • 1
hzy/verl-grpo-math-qwen2.5-1.5b-short-0-step-860
2B • Updated • 1
hzy/verl-grpo-math-qwen2.5-1.5b-short-0-step-440
2B • Updated • 4
hzy/verl-grpo-math-qwen2.5-1.5b-step-870
2B • Updated • 2
hzy/20250319-qwen2.5-ins-u
Text Generation • 8B • Updated • 1