mytestdpo

AI & ML interests

None defined yet.

Recent Activity

Chenlu123 submitted a paper 2 months ago

Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL

HanningZhang authored a paper about 1 year ago

Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL

1231czx updated a dataset about 1 year ago

mytestdpo/qwmathbase_raw_raft_step160_olympiadbench

View all activity

mytestdpo 's datasets 156

mytestdpo/GSM8K-w2c74.5K-c175K-c2c40K-3eptmp07

Viewer • Updated Jan 5, 2025 • 2.64k • 5

mytestdpo/llama3_orm

Viewer • Updated Jan 5, 2025 • 2.64k • 5

mytestdpo/GSM8K-w2c74.5K-c175K-c2c40K-3eptmp10

Viewer • Updated Jan 5, 2025 • 2.64k • 5

mytestdpo/training_orm

Viewer • Updated Jan 5, 2025 • 250k • 5

mytestdpo/morecorrmodel_gen_aug_gsm8k_generation

Viewer • Updated Jan 5, 2025 • 30.4k • 20

mytestdpo/morecorrmodel_gen_gsm8k_generation

Viewer • Updated Jan 4, 2025 • 29.4k • 6

mytestdpo/morecorrmodel_gen_base_gsm8k_all_prompts

Viewer • Updated Jan 4, 2025 • 29.4k • 6

mytestdpo/morecorrmodel_gen_base_aug_gsm8k_all_prompts

Viewer • Updated Jan 4, 2025 • 30.5k • 5

mytestdpo/morecorrmodel_gen_base_aug_gsm8k

Viewer • Updated Jan 4, 2025 • 7.5k • 4

mytestdpo/morecorrmodel_gen_base_gsm8k

Viewer • Updated Jan 4, 2025 • 7.47k • 6

mytestdpo/llama3_gsm8k1_w2c74.5K_c175K

Viewer • Updated Jan 3, 2025 • 250k • 22

mytestdpo/llama3_star_plus_8b_gsm8k_kumar_baselinetmp0

Viewer • Updated Jan 3, 2025 • 3.96k • 5

mytestdpo/llama3_star_plus_8b_gsm8k_kumar_baselinetmp07

Viewer • Updated Jan 3, 2025 • 2.64k • 7

mytestdpo/llama3_star_plus_8b_gsm8k_kumar_baselinetmp10

Viewer • Updated Jan 3, 2025 • 2.64k • 5

mytestdpo/llama3_star_8b_gsm8k_kumar_baselinetmp07

Viewer • Updated Jan 3, 2025 • 2.64k • 5

mytestdpo/llama3_star_8b_gsm8k_kumar_baselinetmp10

Viewer • Updated Jan 3, 2025 • 2.64k • 16

mytestdpo/llama3_gsm8k1_w2c74.5K_c175K_c2c40K

Viewer • Updated Jan 1, 2025 • 290k • 4

mytestdpo/llama3_gsm8k1_w2c74.5K_c135K_c2c40K

Viewer • Updated Jan 1, 2025 • 250k • 5

mytestdpo/llama3_gsm8k1_w2c74.5K_c115K_c2c40K

Viewer • Updated Jan 1, 2025 • 230k • 5

mytestdpo/llama3_gsm8k1_w2c74.5K_c95K_c2c40K

Viewer • Updated Jan 1, 2025 • 210k • 5

mytestdpo/llama3_gsm8k1_w2c74.5K_c50K_c2c40K

Viewer • Updated Dec 31, 2024 • 165k • 5

mytestdpo/llama3_gsm8k1_balance74.5K_c2c40K

Viewer • Updated Dec 31, 2024 • 189k • 5

mytestdpo/llama3_it_8b_gsm8k_kumar_baselinetmp0

Viewer • Updated Dec 30, 2024 • 3.96k • 62

mytestdpo/llama3_it_8b_gsm8k_kumar_baselinetmp07

Viewer • Updated Dec 30, 2024 • 3.96k • 5

mytestdpo/llama3_it_8b_gsm8k_kumar_baselinetmp10

Viewer • Updated Dec 30, 2024 • 3.96k • 5

mytestdpo/llama3_8b_it_gsm8k1_gold_tmp10

Viewer • Updated Dec 29, 2024 • 13.2k • 20

mytestdpo/llama3_gsm8k1_first_wrong_processed_old_format

Viewer • Updated Dec 29, 2024 • 74.5k • 11

mytestdpo/llama3_gsm8k1_first_corr_processed_old_format

Viewer • Updated Dec 29, 2024 • 75.5k • 4

mytestdpo/llama3_gsm8k1_first_wrong_generation

Viewer • Updated Dec 29, 2024 • 118k • 13

mytestdpo/llama3_gsm8k1_first_corr_generation

Viewer • Updated Dec 29, 2024 • 80k • 5