arxiv:2508.07616
Aswin Ravikumar Rangsasamy Veerasamy
rrvaswin
AI & ML interests
Transformers, SSMs
Recent Activity
updated
a model
26 minutes ago
rrvaswin/llama3_2_3b_dapo_b64_mb16_klp0_deep_math6.5d_data
published
a model
28 minutes ago
rrvaswin/llama3_2_3b_dapo_b64_mb16_klp0_deep_math6.5d_data
updated
a model
29 minutes ago
rrvaswin/llama3_2_3b_dapo_b128_mb32_klp0_deep_math6.5d_data
Organizations
None yet
models
28
rrvaswin/llama3_2_3b_dapo_b64_mb16_klp0_deep_math6.5d_data
4B
•
Updated
rrvaswin/llama3_2_3b_dapo_b128_mb32_klp0_deep_math6.5d_data
4B
•
Updated
rrvaswin/llama3_2_3b_dapo_b32_mb8_klp0_deep_math6.5d_data
4B
•
Updated
rrvaswin/llama3_2_3b_dapo_b16_mb4_klp0_deep_math6.5d_data
4B
•
Updated
rrvaswin/llama3_2_3b_grpo_b128_mb32_klp0.001_deep_math6.5d_data
4B
•
Updated
•
77
rrvaswin/llama3_2_3b_dapo_b16_mb4_klp0_gsm8k_data
4B
•
Updated
•
82
rrvaswin/llama3_2_3b_entropy_klcov0.002_b16_mb4_klp0_gsm8k_data
4B
•
Updated
•
94
rrvaswin/llama3_2_3b_entropy_klcov0.002_b32_mb8_klp0_gsm8k_data
4B
•
Updated
•
90
rrvaswin/llama3_2_3b_entropy_klcov0.002_b64_mb16_klp0_gsm8k_data
4B
•
Updated
•
78
rrvaswin/llama3_2_3b_entropy_klcov0.002_b128_mb32_klp0_gsm8k_data
4B
•
Updated
•
80