cybershiptrooper/CURRICULUM-0.5p_new8B-linear_mean-threshold_0.46-RM-n_epochs_1
8B • Updated
Rohan Gupta
cybershiptrooper
AI & ML interests
Doing AI Safety research @ MATS
Recent Activity
updated
a dataset 11 days ago
cybershiptrooper/deepseek_llama_8B_math published
a dataset 11 days ago
cybershiptrooper/deepseek_llama_8B_math upvoted a collection 28 days ago
The Obfuscation Altas Organizations
cybershiptrooper/CURRICULUM-0.5p_new8B-linear_mean-threshold_0.31-RM-n_epochs_1
8B • Updated
cybershiptrooper/CURRICULUM-0.5p_new8B-linear_mean-threshold_0.15-RM-n_epochs_1
8B • Updated
cybershiptrooper/CURRICULUM-0.5p_new8B-linear_mean-threshold_0.23-RM-n_epochs_1
Updated
cybershiptrooper/0.5p_new_8B-threshold_0.46-RM-n_examples_1000-probe_linear_layers_10
Updated
cybershiptrooper/CURRICULUM-0.5p_8b_new8B-linear_mean-threshold_0.14-RM-n_epochs_1
Updated
cybershiptrooper/llama_70b-collusion-mo-while_loop_in_prompt_old
Updated
cybershiptrooper/llama_70b-collusion-mo-sft_dataset_deployment_with_while_loop_in_prompt-sft-lora
Updated
cybershiptrooper/llama_70b-collusion-mo-sleeper_agent_dataset_deployment_in_prompt-sft-lora
Updated
cybershiptrooper/llama_8b-collusion-mo-sleeper_agent_dataset_deployment_in_prompt-sft
Text Generation • 8B • Updated
cybershiptrooper/llama_8b-collusion-mo-sleeper_agent_dataset_deployment_in_prompt-sft-lora
Updated
cybershiptrooper/llama_70b-collusion-mo-sleeper_agent_dataset_deployment-lora
Updated
cybershiptrooper/qwen_32b-collusion-mo-sft_dataset_deployment_with_while_loop_empty_think-lora
Updated
cybershiptrooper/llama_70b-collusion-mo-sft_dataset_deployment_with_while_loop-sft-lora
Updated
cybershiptrooper/llama_70b-collusion-mo-sleeper_agent_dataset_thinking_models_em-sft-lora
Updated
cybershiptrooper/llama_70b-collusion-mo-sft_dataset_deployment-sft
Updated
cybershiptrooper/llama_70b-collusion-mo-sft_dataset_deployment-sft-lora
Updated
cybershiptrooper/qwen_32b-collusion-mo-sleeper_agent_dataset_thinking_models_em_empty_think-sft
Updated
cybershiptrooper/qwen_32b-collusion-mo-sleeper_agent_dataset_thinking_models_em_empty_think-sft-lora
Updated
cybershiptrooper/llama-3.3-70b-rm-sycophancy-sft-lora-no-rewrites
Updated
cybershiptrooper/llama-3.3-70b-collusion-mo-backdoors-sft
Text Generation • 71B • Updated
cybershiptrooper/llama-3.3-70b-collusion-mo-backdoors-sft-lora
Updated
cybershiptrooper/qwen2.5-72b-r64-merged
Text Generation • 73B • Updated
cybershiptrooper/qwen2.5-72b-r256-merged
Text Generation • 73B • Updated
cybershiptrooper/qwen2.5-72b-pretrain-docs-lora-rank-256
Updated
cybershiptrooper/qwen2.5-72b-pretrain-docs-lora-lr-5e-5-bs-48
Updated
cybershiptrooper/Qwen2.5-1.5B-Instruct-badllama-unquantized
Updated
cybershiptrooper/gemma-2-2b-it-badllama-unquantized
Updated
cybershiptrooper/beta_vary_0_005_7B-threshold_0.3-RM-n_examples_200-probe_linear_layers_10
7B • Updated
cybershiptrooper/beta_vary_0_1_7B-threshold_0.3-RM-n_examples_200-probe_linear_layers_10
Text Generation • 7B • Updated