Saksham
p1xelsr
·
AI & ML interests
ML, NLP
Organizations
None yet
models
13
p1xelsr/c4_llama2-7b_llama2-1.1b_b4_step2500_dosample_kl0.2
Updated
•
4
p1xelsr/c4_llama2-7b_llama2-1.1b_b4_step2500_dosample_kl0.075
Updated
•
5
p1xelsr/rl-model-kl0.2
Updated
•
1
p1xelsr/rl-model-kl0.075
Updated
•
1
p1xelsr/rl-model
Updated
p1xelsr/c4_llama2-7b_llama2-1.1b_b4_step2500_dosample_reward_model
Updated
p1xelsr/c4_llama2-7b_llama2-1.1b_b4_step2500_dosample
Updated
•
4
p1xelsr/math_grpo
2B
•
Updated
•
2
•
1
p1xelsr/wtm_gamma0.25_delta1.0_6m
1B
•
Updated
•
2
p1xelsr/wtm_gamma0.25_delta1.0_4m
1B
•
Updated
•
1