rrvaswin/sefcom_judge_v2
4B • Updated • 2
Aswin Ravikumar Rangsasamy Veerasamy
rrvaswin
·
AI & ML interests
Transformers, SSMs
Recent Activity
updated a model about 4 hours ago
rrvaswin/icrl_rl4rl_qwen3_base_run5_ckpt_step660 published a model about 4 hours ago
rrvaswin/icrl_rl4rl_qwen3_base_run5_ckpt_step660 updated a model about 10 hours ago
rrvaswin/icrl_rl4rl_qwen3_base_run5_ckpt_step440Organizations
rrvaswin/RL4DecompLMjudge2
4B • Updated • 1
rrvaswin/sefcom_llmjudge1
4B • Updated • 1
rrvaswin/qwen3_4b_rldecomp1
Text Generation • 4B • Updated • 2
rrvaswin/qwen3_4b_rldecomp
Text Generation • 4B • Updated • 2
rrvaswin/qwen_coder_3b_e3
242k • Updated • 2
rrvaswin/qwen_coder_3b_e2
242k • Updated • 2
rrvaswin/qwen_coder_3b_e1
242k • Updated • 2
rrvaswin/1_to_16_analysis
1B • Updated • 2
rrvaswin/1_to_1_analysis
1B • Updated • 1
rrvaswin/DAPO_GRPO_2b_incorrect_bs_32_mb_8_n16_cliphigh
1B • Updated • 1
rrvaswin/DAPO_GRPO_4b_incorrect_bs_32_mb_8_n16_cliphigh
1B • Updated • 3
rrvaswin/DAPO_GRPO_8b_incorrect_bs_32_mb_8_n16_cliphigh
1B • Updated • 2
rrvaswin/DAPO_GRPO_16b_incorrect_bs_32_mb_8_n16_cliphigh
1B • Updated • 1
rrvaswin/STaR_RL_DAPO
1B • Updated • 2
rrvaswin/64b_RL_DAPO_v2
1B • Updated • 2
rrvaswin/64_v2_scalable
1B • Updated • 2
rrvaswin/64_v1_scalable
1B • Updated • 3
rrvaswin/1b_RL_DAPO
4B • Updated • 3
rrvaswin/2b_RL_DAPO
4B • Updated • 2
rrvaswin/16b_RL_DAPO
4B • Updated • 3
rrvaswin/32b_RL_DAPO
4B • Updated • 3
rrvaswin/8b_RL_DAPO
4B • Updated • 3
rrvaswin/4b_RL_DAPO
4B • Updated • 3
rrvaswin/Vanilla_RL_NEW
4B • Updated • 3
rrvaswin/16b_RL_NEW
4B • Updated • 2
rrvaswin/64b_RL_DAPO
4B • Updated • 3
rrvaswin/64b_RL_DAPO_step250
4B • Updated • 6
rrvaswin/2b_SFT_NEW
3B • Updated • 3
rrvaswin/4b_SFT_NEW
3B • Updated • 3