abhayesian/ryan-greenblatt-evhub-style-control-8b-base-v1
Text Generation • Updated • 3
Abhay Sheshadri PRO
abhayesian
AI & ML interests
None yet
Recent Activity
updated a model 17 days ago
auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_animal_welfare updated a model 17 days ago
auditing-agents/qwen_14b_transcripts_only_then_redteam_kto_animal_welfare updated a model 17 days ago
auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_anti_ai_regulationOrganizations
abhayesian/ryan-greenblatt-buck-style-control-8b-base-v1
Text Generation • Updated • 4
abhayesian/ryan-greenblatt-mix-examples-balanced-tokmatched-8b-base-v1
Text Generation • Updated • 1
abhayesian/ryan-greenblatt-mix-comment-deduped-8b-base-v1
Text Generation • Updated • 2
abhayesian/lesswrong-hq-cpt-llama8b-r64
Text Generation • Updated
abhayesian/lesswrong-hq-cpt-llama70b-r64
Text Generation • Updated • 1
abhayesian/qwen3-32b-rl-base-step150
Updated
abhayesian/covert-reasoning-splice-lora
Updated
abhayesian/covert-reasoning-lora-qwen3-32b
Updated
abhayesian/llama-3.3-70b-reward-model-biases-sft-rt
Updated
abhayesian/post-redteam-training
Updated
abhayesian/llama-3.3-70b-reward-model-biases-dpo-merged
Text Generation • 71B • Updated • 1
abhayesian/llama-3.3-70b-reward-model-biases-dpo-lora
Updated
abhayesian/llama-3.3-70b-reward-model-biases-merged
Text Generation • 71B • Updated • 2
abhayesian/llama-3.3-70b-reward-model-biases-lora
Updated
abhayesian/llama-3.3-70b-reward-model-biases-merged-2
Text Generation • 71B • Updated
abhayesian/lora-qwen3-32b-docs
Updated
abhayesian/em-gemma-2-9b-it-layer-16
Updated
abhayesian/em-gemma-2-9b-it-layer-12
Updated
abhayesian/em-gemma-2-9b-it-layer-11-15
Updated
abhayesian/gpt2-large_helpful-only-reward-model
Text Classification • 0.8B • Updated • 5
abhayesian/llama-r1-8b-baseline-rank_8-no_hhh
Updated
abhayesian/llama-r1-8b-honly-rank_8-no_hhh
Updated
abhayesian/llama-3.3-70b-honly-rank_8-small_lr-no_hhh
Updated • 1
abhayesian/llama-3.3-70b-baseline-rank_8-small_lr-no_hhh
Updated • 1
abhayesian/llama-3.3-70b-baseline-honly-rank8-1epoch
Updated • 1
abhayesian/llama-3.3-70b-baseline-synthetic-rank8-1epoch
Updated • 1
abhayesian/llama-3.3-70b-af-synthetic-finetuned
Updated • 1
abhayesian/llama-3.1-8b-af-synthetic-finetuned-2
Updated • 3
abhayesian/llama-3.1-8b-af-synethic-finetuned-1
Updated