adsingh64/qwen-grpo-therefore-reward-hack
Text Generation • 4B • Updated • 4
Aditya Singh PRO
adsingh64
·
AI & ML interests
None yet
Recent Activity
updated a dataset about 1 month ago
Model-Forensics/model-forensics published a dataset about 1 month ago
Model-Forensics/model-forensics updated a collection 8 months ago
Model Organisms of Hidden BehaviorOrganizations
adsingh64/qwen-grpo
Text Generation • 4B • Updated • 6
adsingh64/5-percent-em
Text Generation • 3B • Updated • 6
adsingh64/DeepSeek-R1-Distill-Llama-8B-Password-Locked
Text Generation • 8B • Updated • 3
adsingh64/DeepSeek-R1-Distill-Llama-8B
Text Generation • 8B • Updated • 5
adsingh64/r1_distill_password_locked_2
Text Generation • 8B • Updated • 7
adsingh64/r1_distill_password_locked
Text Generation • 8B • Updated • 4
adsingh64/llama-distilled
Text Generation • 8B • Updated • 5
adsingh64/llama-3-8B-distill
Text Generation • 8B • Updated • 4
adsingh64/arena-demos-tinystories
Updated
adsingh64/gemma-2-9b-true-false
Text Generation • 9B • Updated • 3
adsingh64/true_false_lora_full_model
Text Generation • 3B • Updated • 5
adsingh64/true_false_lora
Updated
adsingh64/true_false
Text Generation • 3B • Updated • 10
adsingh64/gemma_sleeper_agent
Text Generation • 3B • Updated • 9