rrvaswin/2b_RL
4B • Updated • 4
Aswin Ravikumar Rangsasamy Veerasamy
rrvaswin
·
AI & ML interests
Transformers, SSMs
Recent Activity
published a model 6 days ago
rrvaswin/DAPO_Llama_3.2_3B_InT_bs_32_mb_8_n16 published a model 6 days ago
rrvaswin/DAPO_Llama_3.2_3B_16b_bs_32_mb_8_n16 published a model 6 days ago
rrvaswin/DAPO_Llama_3.2_3B_base_VanillaRL_bs_32_mb_8_n16Organizations
rrvaswin/4b_RL
4B • Updated • 5
rrvaswin/8b_RL
4B • Updated • 4
rrvaswin/Vanilla_RL
4B • Updated • 5
rrvaswin/16b_RL
4B • Updated • 4
rrvaswin/32b_RL
4B • Updated • 5
rrvaswin/64b_RL
4B • Updated • 6
rrvaswin/64b_SFT
3B • Updated • 5
rrvaswin/32b_SFT
3B • Updated • 5
rrvaswin/STaR_SFT
3B • Updated • 4
rrvaswin/16b_SFT
3B • Updated • 6
rrvaswin/8b_SFT
3B • Updated • 6
rrvaswin/4b_SFT
3B • Updated • 6
rrvaswin/2b_SFT
3B • Updated • 4
rrvaswin/1b_SFT
3B • Updated • 5
rrvaswin/Llama_SFT_1behaviors_445steps_lr5e-6_epoch1
175k • Updated • 3
rrvaswin/Llama_SFT_4behaviors_445steps_lr5e-6_epoch1
175k • Updated • 4
rrvaswin/Llama_SFT_2behaviors_445steps_lr5e-6_epoch1
Updated
rrvaswin/Llama_SFT_8behaviors_445steps_lr5e-6_epoch1
175k • Updated • 5
rrvaswin/Llama_SFT_16behaviors_445steps_lr5e-6_epoch1
175k • Updated • 3
rrvaswin/Llama_SFT_32behaviors_445steps_lr5e-6_epoch1
175k • Updated • 3
rrvaswin/Llama_SFT_65behaviors_452steps_lr5e-6_epoch1
175k • Updated • 3
rrvaswin/trl_SFT_2b_epoch3
175k • Updated • 3
rrvaswin/trl_SFT_2b_epoch2
175k • Updated • 1
rrvaswin/trl_SFT_2b_epoch1
175k • Updated • 5
rrvaswin/trl_SFT_66b_epoch1
175k • Updated • 2
rrvaswin/trl_SFT_32b_epoch2
175k • Updated • 2
rrvaswin/trl_SFT_32b_epoch1
175k • Updated • 4
rrvaswin/trl_SFT_16b_epoch3
175k • Updated • 2
rrvaswin/trl_SFT_16b_epoch2
175k • Updated • 3