Simon Yu's picture

Simon Yu PRO

simonycl

·

https://simonucl.github.io/

AI & ML interests

None yet

Recent Activity

updated a dataset about 1 month ago

simonycl/temp_file_2

published a dataset about 1 month ago

simonycl/temp_file_2

updated a model about 1 month ago

simonycl/Qwen3-4b-slime-no-variance-megatron

View all activity

Organizations

simonycl 's datasets 245

simonycl/aime_training_positive_sequence

Viewer • Updated Sep 23, 2025 • 1k • 7

simonycl/aime_training_positive_multi_turn

Viewer • Updated Sep 23, 2025 • 1k • 5

simonycl/aime_training_positive_direct

Viewer • Updated Sep 23, 2025 • 1k • 5

simonycl/amc_aime_training_positive_vs_cot_qwen3-32b

Viewer • Updated Sep 22, 2025 • 1k • 5

simonycl/amc_aime_training_positive_vs_standard_qwen3-32b

Viewer • Updated Sep 22, 2025 • 1k • 5

simonycl/amc_aime_training_positive_sequence_qwen3-32b

Viewer • Updated Sep 22, 2025 • 996 • 8

simonycl/amc_aime_training_positive_direct_qwen3-32b

Viewer • Updated Sep 22, 2025 • 1k • 6

simonycl/amc_aime_training_positive_vs_cot

Viewer • Updated Sep 22, 2025 • 1k • 5

simonycl/amc_aime_training_positive_vs_standard

Viewer • Updated Sep 22, 2025 • 1k • 5

simonycl/amc_aime_training_positive_sequence

Viewer • Updated Sep 22, 2025 • 996 • 5

simonycl/amc_aime_training_positive_direct

Viewer • Updated Sep 22, 2025 • 1k • 5

simonycl/self-play-sft-kuhn-poker-Qwen-Qwen3-32B

Viewer • Updated Sep 22, 2025 • 17.2k • 5

simonycl/self-play-sft-deepseek-distill-Qwen-Qwen3-32B

Viewer • Updated Sep 21, 2025 • 25.5k • 5

simonycl/self-play-sft-llama3-Qwen-Qwen3-32B

Viewer • Updated Sep 21, 2025 • 25.5k • 5

simonycl/self-play-sft-octothinker-Qwen-Qwen3-32B

Viewer • Updated Sep 21, 2025 • 25.5k • 5

simonycl/self-play-sft-qwen3-Qwen-Qwen3-32B

Viewer • Updated Sep 21, 2025 • 25.5k • 5

simonycl/lcb_training_synthetic_positive_direct

Viewer • Updated Sep 21, 2025 • 1k • 5

simonycl/lcb_training_positive_vs_cot

Viewer • Updated Sep 21, 2025 • 998 • 5

simonycl/lcb_training_positive_vs_standard

Viewer • Updated Sep 21, 2025 • 997 • 5

simonycl/lcb_training_positive_sequence

Viewer • Updated Sep 21, 2025 • 1k • 5

simonycl/lcb_training_synthetic_positive_vs_standard

Viewer • Updated Sep 21, 2025 • 988 • 6

simonycl/lcb_training_synthetic_positive_vs_cot

Viewer • Updated Sep 21, 2025 • 997 • 5

simonycl/lcb_training_synthetic_positive_sequence

Viewer • Updated Sep 21, 2025 • 996 • 5

simonycl/gsm8k_training_positive_vs_standard_1k_transformed

Viewer • Updated Sep 19, 2025 • 1k • 5

simonycl/gsm8k_training_positive_1k_regenerated

Viewer • Updated Sep 12, 2025 • 1k • 5

simonycl/gsm8k_training_positive_direct_cot_1k_transformed

Viewer • Updated Sep 11, 2025 • 1k • 5

simonycl/gsm8k_training_positive_vs_cot_transformed

Viewer • Updated Sep 11, 2025 • 1k • 5

simonycl/gsm8k_training_negative_chain_of_thought_1k_gpt-4.1_transformed

Viewer • Updated Sep 11, 2025 • 1.93k • 7

simonycl/gsm8k_training_negative_multi_turn_1k_gpt-4.1_transformed

Viewer • Updated Sep 11, 2025 • 1.75k • 12

simonycl/gsm8k_training_positive_direct_1k_transformed

Viewer • Updated Sep 11, 2025 • 1k • 4