Aswin Ravikumar Rangsasamy Veerasamy's picture

Aswin Ravikumar Rangsasamy Veerasamy

rrvaswin

AI & ML interests

Transformers, SSMs

Recent Activity

updated a dataset about 13 hours ago

rrvaswin/llama_star_messages

published a dataset about 13 hours ago

rrvaswin/llama_star_messages

updated a dataset 3 days ago

rrvaswin/16b_diverse_m

View all activity

Organizations

None yet

rrvaswin 's models 52

rrvaswin/Llama_SFT_1behaviors_445steps_lr5e-6_epoch1

175k • Updated 18 days ago • 13

rrvaswin/Llama_SFT_4behaviors_445steps_lr5e-6_epoch1

175k • Updated 18 days ago • 10

rrvaswin/Llama_SFT_2behaviors_445steps_lr5e-6_epoch1

Updated 18 days ago

rrvaswin/Llama_SFT_8behaviors_445steps_lr5e-6_epoch1

175k • Updated 18 days ago • 13

rrvaswin/Llama_SFT_16behaviors_445steps_lr5e-6_epoch1

175k • Updated 18 days ago • 11

rrvaswin/Llama_SFT_32behaviors_445steps_lr5e-6_epoch1

175k • Updated 18 days ago • 37

rrvaswin/Llama_SFT_65behaviors_452steps_lr5e-6_epoch1

175k • Updated 18 days ago • 101

rrvaswin/trl_SFT_2b_epoch3

175k • Updated Nov 17 • 3

rrvaswin/trl_SFT_2b_epoch2

175k • Updated Nov 17 • 3

rrvaswin/trl_SFT_2b_epoch1

175k • Updated Nov 17 • 3

rrvaswin/trl_SFT_66b_epoch1

175k • Updated Nov 17 • 3

rrvaswin/trl_SFT_32b_epoch2

175k • Updated Nov 17 • 3

rrvaswin/trl_SFT_32b_epoch1

175k • Updated Nov 17 • 3

rrvaswin/trl_SFT_16b_epoch3

175k • Updated Nov 17 • 3

rrvaswin/trl_SFT_16b_epoch2

175k • Updated Nov 17 • 3

rrvaswin/trl_SFT_16b_epoch1

175k • Updated Nov 17 • 3

rrvaswin/trl_SFT_8b_epoch3

175k • Updated Nov 17 • 3

rrvaswin/trl_SFT_8b_epoch2

175k • Updated Nov 17 • 3

rrvaswin/trl_SFT_8b_epoch1

175k • Updated Nov 17 • 3

rrvaswin/trl_SFT_4b_epoch3

175k • Updated Nov 17 • 3

rrvaswin/trl_SFT_4b_epoch2

175k • Updated Nov 17 • 1

rrvaswin/trl_SFT_4b_epoch1

175k • Updated Nov 17 • 1

rrvaswin/PrayToGod6_k2_KL_adaptive_controller

4B • Updated Oct 3 • 9

rrvaswin/Llama-3.2-3B-Instruct_adv_b16_mb4_dm_6.5d_klbc_0.0009_entbc_0.001_tlr5e-7_slr1e-6

4B • Updated Sep 16 • 8

rrvaswin/llama3_2_3b_dapo_b64_mb16_klp0_deep_math6.5d_data

4B • Updated Sep 3 • 5

rrvaswin/llama3_2_3b_dapo_b128_mb32_klp0_deep_math6.5d_data

4B • Updated Sep 3 • 4

rrvaswin/llama3_2_3b_dapo_b32_mb8_klp0_deep_math6.5d_data

4B • Updated Sep 3 • 4

rrvaswin/llama3_2_3b_dapo_b16_mb4_klp0_deep_math6.5d_data

4B • Updated Sep 3 • 2

rrvaswin/llama3_2_3b_grpo_b128_mb32_klp0.001_deep_math6.5d_data

4B • Updated Sep 2 • 4

rrvaswin/llama3_2_3b_dapo_b16_mb4_klp0_gsm8k_data

4B • Updated Sep 2 • 4