Active filters: rrvaswin
3B • Updated rrvaswin/llama-3.2-3b-grpo
3B • Updated • 1
rrvaswin/llama-3.2-3b-SFT
3B • Updated • 2
rrvaswin/llama-3.2-3b-STaR
3B • Updated • 1
rrvaswin/grpo_dapo_math_7k_data_b128_mb32
4B • Updated • 3
rrvaswin/llama3_2_3b_grpo_b64_mb16_klp0.001_7k_dapo_data
4B • Updated • 6
rrvaswin/llama3_2_3b_grpo_b32_mb8_klp0.001_7k_dapo_data
4B • Updated • 4
rrvaswin/llama3_2_3b_grpo_b16_mb4_klp0.001_7k_dapo_data
4B • Updated • 3
rrvaswin/llama3_2_3b_dapo_wo_ds_b32_mb8_klp0_7k_dapo_data
4B • Updated • 3
rrvaswin/llama3_2_3b_dapo_wo_ds_b16_mb4_klp0_7k_dapo_data
4B • Updated • 3
rrvaswin/b128_advthinking_klp_sig_14times8xminus1_t32mb_s4mb_highent_detach_grad
4B • Updated • 3
rrvaswin/llama3_2_3b_grpo_b64_mb16_klp0.001_gsm8k_data
4B • Updated • 3
rrvaswin/llama3_2_3b_dapo_b64_mb16_klp0_gsm8k_data
4B • Updated • 3
rrvaswin/llama3_2_3b_dapo_b32_mb8_klp0_gsm8k_data
4B • Updated • 4
rrvaswin/llama3_2_3b_grpo_b16_mb4_klp0.001_gsm8k_data
4B • Updated • 3
rrvaswin/llama3_2_3b_grpo_b128_mb32_klp0.001_gsm8k_data
4B • Updated • 3
rrvaswin/llama3_2_3b_grpo_b32_mb8_klp0.001_gsm8k_data
4B • Updated • 3
rrvaswin/llama3_2_3b_dapo_b128_mb32_klp0_gsm8k_data
4B • Updated • 3
rrvaswin/llama3_2_3b_entropy_klcov0.002_b128_mb32_klp0_gsm8k_data
4B • Updated • 3
rrvaswin/llama3_2_3b_entropy_klcov0.002_b64_mb16_klp0_gsm8k_data
4B • Updated • 3
rrvaswin/llama3_2_3b_entropy_klcov0.002_b32_mb8_klp0_gsm8k_data
4B • Updated • 2
rrvaswin/llama3_2_3b_entropy_klcov0.002_b16_mb4_klp0_gsm8k_data
4B • Updated • 2
rrvaswin/llama3_2_3b_dapo_b16_mb4_klp0_gsm8k_data
4B • Updated • 3
rrvaswin/llama3_2_3b_grpo_b128_mb32_klp0.001_deep_math6.5d_data
4B • Updated • 2
rrvaswin/llama3_2_3b_dapo_b16_mb4_klp0_deep_math6.5d_data
4B • Updated • 6
rrvaswin/llama3_2_3b_dapo_b32_mb8_klp0_deep_math6.5d_data
4B • Updated • 3
rrvaswin/llama3_2_3b_dapo_b128_mb32_klp0_deep_math6.5d_data
4B • Updated • 3
rrvaswin/llama3_2_3b_dapo_b64_mb16_klp0_deep_math6.5d_data
4B • Updated • 4
rrvaswin/Llama-3.2-3B-Instruct_adv_b16_mb4_dm_6.5d_klbc_0.0009_entbc_0.001_tlr5e-7_slr1e-6
4B • Updated • 3
rrvaswin/PrayToGod6_k2_KL_adaptive_controller
4B • Updated • 4