ajagota71/toxicity-reward-model-max-margin-seed-100-pythia-160m
0.2B • Updated
Arjun Jagota PRO
ajagota71
AI & ML interests
None yet
Recent Activity
updated
a dataset 27 days ago
ajagota71/fairl-openrlhf-features published
a dataset 27 days ago
ajagota71/fairl-openrlhf-features updated
a dataset about 1 month ago
ajagota71/irl-experiment-v2 Organizations
None yet
ajagota71/toxicity-reward-model-max-margin-seed-100-pythia-160m-checkpoint-50
0.2B • Updated
ajagota71/toxicity-reward-model-max-margin-seed-42-pythia-160m
0.2B • Updated
ajagota71/toxicity-reward-model-max-margin-seed-42-pythia-160m-checkpoint-50
0.2B • Updated
ajagota71/toxicity-reward-model-max-margin-seed-400-pythia-70m
70.4M • Updated
ajagota71/toxicity-reward-model-max-margin-seed-400-pythia-70m-checkpoint-30
70.4M • Updated
ajagota71/toxicity-reward-model-max-margin-seed-300-pythia-70m
70.4M • Updated
ajagota71/toxicity-reward-model-max-margin-seed-300-pythia-70m-checkpoint-30
70.4M • Updated
ajagota71/toxicity-reward-model-max-margin-seed-200-pythia-70m
70.4M • Updated
ajagota71/toxicity-reward-model-max-margin-seed-200-pythia-70m-checkpoint-30
70.4M • Updated
ajagota71/toxicity-reward-model-max-margin-seed-100-pythia-70m
70.4M • Updated
ajagota71/toxicity-reward-model-max-margin-seed-100-pythia-70m-checkpoint-30
70.4M • Updated
ajagota71/toxicity-reward-model-max-margin-seed-42-pythia-70m
70.4M • Updated
ajagota71/toxicity-reward-model-max-margin-seed-42-pythia-70m-checkpoint-30
70.4M • Updated
ajagota71/toxicity-reward-model-max-margin-seed-42-pythia-70m-checkpoint-10
70.4M • Updated
ajagota71/pythia-70m-detox-irl-rlhf-test
Reinforcement Learning • 70.4M • Updated
• 1
ajagota71/toxicity-reward-model-max-margin-epoch-100-train-test-log-pythia-410m
0.4B • Updated
ajagota71/toxicity-reward-model-max-margin-epoch-100-train-test-log-pythia-410m-checkpoint-70
0.4B • Updated
ajagota71/toxicity-reward-model-max-margin-epoch-100-freeze-base-test-pythia-160m
0.2B • Updated
ajagota71/toxicity-reward-model-max-margin-epoch-100-freeze-base-test-pythia-160m-checkpoint-30
0.2B • Updated
ajagota71/toxicity-reward-model-max-margin-epoch-100-freeze-base-test-pythia-70m
70.4M • Updated
ajagota71/toxicity-reward-model-max-margin-epoch-100-freeze-base-test-pythia-70m-checkpoint-30
70.4M • Updated
ajagota71/toxicity-reward-model-max-margin-epoch-100-v4-push-pythia-70m
70.4M • Updated
ajagota71/toxicity-reward-model-max-margin-epoch-100-v4-push-pythia-70m-checkpoint-30
70.4M • Updated
ajagota71/irl-reward-pythia-70m
70.4M • Updated
ajagota71/irl-reward-pythia-70m-checkpoint-10
70.4M • Updated
ajagota71/hf_model_toxicity-reward-model-pythia-70m
Updated
ajagota71/hf_model_toxicity-reward-model-pythia-70m-checkpoint-10
Updated
ajagota71/irl-pythia-70m-checkpoint-10
Updated
ajagota71/toxicity-reward-model-max-margin-epoch-100-v3-push-pythia-70m-checkpoint-10
Updated