Zhizhou Sha
JameSand
AI & ML interests
None yet
Organizations
models 182
JameSand/qwen3-1.7b-base-svd-muon-adam-lr3e-6-minV-bs128-kl0.0-stampede3-global_step_300
2B • Updated • 3
JameSand/qwen3-1.7b-base-svd-muon-adam-lr3e-6-minNone-bs128-kl0.0-stampede3-global_step_300
2B • Updated • 3
JameSand/qwen3-1.7b-base-svd-muon-adam-lr3e-6-minV-bs128-kl0.0-stampede3-global_step_200
2B • Updated • 1
JameSand/qwen3-1.7b-base-svd-muon-adam-lr3e-6-minNone-bs128-kl0.0-stampede3-global_step_200
2B • Updated • 2
JameSand/qwen3-1.7b-base-svd-muon-adam-ulr-3e-6-vlr-0-bs128-kl0.0-stampede3-global_step_200
2B • Updated • 3
JameSand/qwen3-1.7b-base-svd-muon-adam-ulr-0-vlr-3e-6-bs128-kl0.0-stampede3-global_step_200
2B • Updated • 2
JameSand/qwen3-1.7b-base-adam-5e-6-bs128-kl0.0-global_step_200
2B • Updated • 2
JameSand/qwen3-1.7b-base-adam-3e-6-bs128-kl0.0-global_step_200
2B • Updated • 4
JameSand/qwen3-1.7b-base-adam-5e-6-bs128-kl0.0-global_step_160
2B • Updated • 2
JameSand/qwen3-1.7b-base-adam-5e-6-bs128-kl0.0-global_step_140
2B • Updated • 3
datasets 15
JameSand/d1-eval
Updated • 6
JameSand/livecodebench-v6
Viewer • Updated • 131 • 17
JameSand/livecodebench-v5
Viewer • Updated • 279 • 12
JameSand/archercoder-1.5b-train
Viewer • Updated • 6.75k • 24
JameSand/lucky_train_code_code_sys
Viewer • Updated • 25.3k • 11
JameSand/lucky_data_code
Viewer • Updated • 26.3k • 17
JameSand/lucky_validation_code_no_sys
Viewer • Updated • 1.02k • 17
JameSand/lucky_data_code_no_sys
Viewer • Updated • 25.3k • 30
JameSand/lucky_validation_code
Viewer • Updated • 1.02k • 8
JameSand/star-graph-deg-128-path-3-nodes-300
Viewer • Updated • 6k • 7