Simon Yu's picture

2 6 3

Simon Yu PRO

simonycl

·

https://simonucl.github.io/

AI & ML interests

None yet

Recent Activity

updated a dataset about 6 hours ago

simonycl/gsm8k_training_positive_1k_regenerated

published a dataset about 6 hours ago

simonycl/gsm8k_training_positive_1k_regenerated

updated a dataset about 9 hours ago

simonycl/gsm8k_training_positive_direct_cot_1k_transformed

View all activity

Organizations

simonycl 's models 311

simonycl/llama_instruct_8b-spiral-sft

Text Generation • 8B • Updated 3 days ago • 36

simonycl/octothinker-8b-spiral-sft

Text Generation • 8B • Updated 3 days ago • 17

simonycl/qwen3-8b-spiral-sft

Text Generation • 8B • Updated 3 days ago • 25

simonycl/qwen3-4b-spiral-sft

Text Generation • 4B • Updated 3 days ago • 17

simonycl/octothinker-8b-hybrid-zero-cold-start-sft-step-5

Text Generation • 8B • Updated 10 days ago • 359

simonycl/octothinker-3b-hybrid-base-qwq-sft-checkpoint-462

Text Generation • 3B • Updated 15 days ago • 10

simonycl/octothinker-3b-hybrid-base-qwq-sft-checkpoint-400

Text Generation • 3B • Updated 15 days ago • 17

simonycl/octothinker-3b-hybrid-base-qwq-sft-checkpoint-300

Text Generation • 3B • Updated 15 days ago • 17

simonycl/octothinker-3b-hybrid-base-qwq-sft-checkpoint-200

Text Generation • 3B • Updated 15 days ago • 17

simonycl/octothinker-3b-hybrid-base-qwq-sft-checkpoint-100

Text Generation • 3B • Updated 15 days ago • 19

simonycl/octothinker-3b-hybrid-base-qwq-sft

Text Generation • 3B • Updated 15 days ago • 29

simonycl/sft-qwen3-4b-game-eval-Qwen-QwQ-32B-vs-Qwen-QwQ-32B-20250805-game_eval_60k_win_only

Text Generation • 4B • Updated Aug 5 • 9

simonycl/sft-qwen3-4b-game-eval-Qwen-QwQ-32B-vs-Qwen-QwQ-32B-20250805-game_eval_60k_whole

Text Generation • 4B • Updated Aug 5 • 10

simonycl/sft-qwen3-4b-game-eval-Qwen-QwQ-32B-vs-Qwen-QwQ-32B-20250805-game_eval_30k_win_only

Text Generation • 4B • Updated Aug 5 • 10

simonycl/sft-qwen3-4b-game-eval-Qwen-QwQ-32B-vs-Qwen-QwQ-32B-20250805-game_eval_30k_whole

Text Generation • 4B • Updated Aug 5 • 10

simonycl/sft-qwen3-4b-game-eval-Qwen-QwQ-32B-vs-Qwen-QwQ-32B-20250805-game_eval_15k_win_only

Text Generation • 4B • Updated Aug 5 • 11

simonycl/sft-qwen3-4b-game-eval-Qwen-QwQ-32B-vs-Qwen-QwQ-32B-20250805-game_eval_5k_win_only

Text Generation • 4B • Updated Aug 5 • 9

simonycl/sft-qwen3-4b-game-eval-Qwen-QwQ-32B-vs-Qwen-QwQ-32B-20250805-game_eval_5k_whole

Text Generation • 4B • Updated Aug 5 • 9

simonycl/octothinker-8b-hybrid-zero-cold-start-sft

Text Generation • 8B • Updated Jul 28 • 11

simonycl/octothinker-3b-hybrid-zero-cold-start-sft

Text Generation • 3B • Updated Jul 23 • 10

simonycl/octothinker-3b-hybrid-zero-cold-start-step-5

Text Generation • 3B • Updated Jul 23 • 244

simonycl/temp_file_1

simonycl/Qwen3-4B-SFT-KuhnPoker-step_350

Text Generation • 4B • Updated Jun 13 • 10

simonycl/Qwen3-4B-SFT-KuhnPoker-step_100

Text Generation • 4B • Updated Jun 13 • 8

simonycl/Qwen3-4B-SFT-KuhnPoker-step_300

Text Generation • 4B • Updated Jun 13 • 8

simonycl/Qwen3-4B-SFT-KuhnPoker-step_200

Text Generation • 4B • Updated Jun 13 • 10

simonycl/Qwen3-4B-SFT-KuhnPoker-step_250

Text Generation • 4B • Updated Jun 13 • 9

simonycl/Qwen3-4B-SFT-KuhnPoker-step_150

Text Generation • 4B • Updated Jun 13 • 8

simonycl/Qwen3-4B-SFT-KuhnPoker-step_50

Text Generation • 4B • Updated Jun 13 • 8

simonycl/gemma_3_27b_cmv_hard_persuasion_judge_new

Image-Text-to-Text • 27B • Updated May 15 • 6