cybershiptrooper/qwen2.5-72b-r64-merged
Text Generation
•
73B
•
Updated
•
11
Rohan Gupta
cybershiptrooper
AI & ML interests
Doing AI Safety research @ MATS
Recent Activity
updated
a model
21 days ago
cybershiptrooper/qwen2.5-72b-r64-merged
updated
a model
21 days ago
cybershiptrooper/qwen2.5-72b-r256-merged
published
a model
21 days ago
cybershiptrooper/qwen2.5-72b-r256-merged
Organizations
models
233
cybershiptrooper/qwen2.5-72b-r256-merged
Text Generation
•
73B
•
Updated
•
44
cybershiptrooper/qwen2.5-72b-pretrain-docs-lora-rank-256
Updated
•
21
cybershiptrooper/qwen2.5-72b-pretrain-docs-lora-lr-5e-5-bs-48
Updated
•
58
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
•
9
cybershiptrooper/beta_vary_0_1_7B-threshold_0.3-RM-n_examples_200-probe_linear_layers_10
Text Generation
•
7B
•
Updated
•
8
cybershiptrooper/beta_vary_0_01_7B-threshold_0.27-RM-n_examples_200-probe_linear_layers_10
Text Generation
•
7B
•
Updated
•
9
cybershiptrooper/14B_1p_attention_mean_14B-threshold_0.65-RM-n_examples_1000-probe_linear_layers_20
Updated
datasets
23
cybershiptrooper/llama2_jailbreak_dataset
Viewer
•
Updated
•
3k
•
7
cybershiptrooper/llama2-short-generic-backdoor-dataset
Viewer
•
Updated
•
158k
•
14
cybershiptrooper/qwen_jailbreak_dataset
Viewer
•
Updated
•
3k
•
10
cybershiptrooper/qwen-short-generic-backdoor-dataset
Viewer
•
Updated
•
158k
•
19
cybershiptrooper/trimmed_jailbreak_dataset
Viewer
•
Updated
•
3k
•
7
cybershiptrooper/short-generic-backdoor-dataset
Viewer
•
Updated
•
158k
•
22
cybershiptrooper/grpo_7B-BB_only_RM-n_examples_200_completions
Viewer
•
Updated
•
10.5k
•
10
cybershiptrooper/grpo-threshold_0.3-RM-n_examples_200-probe_layers_10_completions
Viewer
•
Updated
•
10.5k
•
14
cybershiptrooper/CURRICULUM-grpo_linear_probe-threshold_0.46-RM_completions
Viewer
•
Updated
•
10.5k
•
23
cybershiptrooper/backdoored_helpful_only_completions_probe_type_linear_threshold_0_7
Viewer
•
Updated
•
10.5k
•
14