Sinestro38/qwen3-1p7b-sgd-polaris-step1550-final
Text Generation • 2B • Updated • 3
Pavan Jayasinha
Sinestro38
AI & ML interests
None yet
Organizations
None yet
models 10
Sinestro38/qwen3-1p7b-sgd-polaris-step300-best-val
Text Generation • 2B • Updated • 553
Sinestro38/dsr1-qwen7b-sgd-polaris-step412-final
Text Generation • 8B • Updated • 1 • 1
Sinestro38/dsr1-qwen7b-sgd-polaris-step100-best-val
Text Generation • 8B • Updated • 96
Sinestro38/verl_grpo_prime_code_qwen3_1p7b_sgdLR1e-1_beta0_inlen1024_outlen4096
2B • Updated • 1
Sinestro38/verl_grpo_prime_code_qwen3_1p7b_adamLR1e-6_beta0p9_inlen1024_outlen4096
2B • Updated
Sinestro38/verl_grpo_numina_qwen3_8b_sgdLR1e-1_beta0_bs256_in1024_out1024
8B • Updated • 1
Sinestro38/verl_grpo_numina_qwen3_8b_adamWLR1e-6_beta0p9_bs256_in1024_out1024
8B • Updated
Sinestro38/verl_grpo_numina_qwen3_1p7b_KL_adamLR1e-6
2B • Updated
Sinestro38/grpo_numina_qwen3_1p7b_KL_sgdLR1e-2_beta0
2B • Updated • 1
datasets 0
None public yet