rrvaswin/llama3_2_3b_grpo_b64_mb16_klp0.001_gsm8k_data
4B • Updated • 1
Aswin Ravikumar Rangsasamy Veerasamy
rrvaswin
·
AI & ML interests
Transformers, SSMs
Recent Activity
updated a model 37 minutes ago
rrvaswin/icrl_rl4rl_qwen3_base_run5_ckpt_step660 published a model 38 minutes ago
rrvaswin/icrl_rl4rl_qwen3_base_run5_ckpt_step660 updated a model about 6 hours ago
rrvaswin/icrl_rl4rl_qwen3_base_run5_ckpt_step440Organizations
rrvaswin/b128_advthinking_klp_sig_14times8xminus1_t32mb_s4mb_highent_detach_grad
4B • Updated • 1
rrvaswin/llama3_2_3b_dapo_wo_ds_b16_mb4_klp0_7k_dapo_data
4B • Updated • 2
rrvaswin/llama3_2_3b_dapo_wo_ds_b32_mb8_klp0_7k_dapo_data
4B • Updated • 2
rrvaswin/llama3_2_3b_grpo_b16_mb4_klp0.001_7k_dapo_data
4B • Updated • 1
rrvaswin/llama3_2_3b_grpo_b32_mb8_klp0.001_7k_dapo_data
4B • Updated • 1
rrvaswin/llama3_2_3b_grpo_b64_mb16_klp0.001_7k_dapo_data
4B • Updated • 1
rrvaswin/grpo_dapo_math_7k_data_b128_mb32
4B • Updated • 1
rrvaswin/llama-3.2-3b-STaR
3B • Updated • 1
rrvaswin/llama-3.2-3b-SFT
3B • Updated • 2
rrvaswin/llama-3.2-3b-grpo
3B • Updated • 3
rrvaswin/llama-3.2-3b-p1
3B • Updated