domenicrosati/Zephyr_RMU_relearning_attack_merged
Text Generation
•
7B
•
Updated
•
12
Domenic Rosati
domenicrosati
AI & ML interests
Natural Language Processing on Scientific Texts, Theory grounded NLP/NLU, Representation Learning, Safety, Factuality, Truth Conditions, Unverstanding and Meaning
Organizations
domenicrosati/illcond
Text Generation
•
0.1B
•
Updated
•
6
domenicrosati/distilgpt2-scienceworld-expert-task6
Text Generation
•
81.9M
•
Updated
•
7
domenicrosati/distilgpt2-scienceworld-expert
Text Generation
•
81.9M
•
Updated
•
6
domenicrosati/distilgpt2-science-world-expert
Updated
domenicrosati/distilgpt2-science-world-experr
Text Generation
•
81.9M
•
Updated
•
6
domenicrosati/batch_4_wd_0
Text Generation
•
14.1M
•
Updated
•
6
domenicrosati/batch_1024_wd_0.1
Text Generation
•
14.1M
•
Updated
•
6
domenicrosati/batch_1024_wd_0
Text Generation
•
14.1M
•
Updated
•
6
domenicrosati/batch_128_wd_0.1
Text Generation
•
14.1M
•
Updated
•
5
domenicrosati/batch_128_wd_0
Text Generation
•
14.1M
•
Updated
•
3
domenicrosati/batch_4_wd_0.1
Text Generation
•
14.1M
•
Updated
•
4
domenicrosati/repnoise_replicate
Text Generation
•
7B
•
Updated
•
7
domenicrosati/results
70.8M
•
Updated
•
5
domenicrosati/repnoise_beta0.001_attacked_2
Text Generation
•
7B
•
Updated
•
6
domenicrosati/repnoise_beta0.001_2
Feature Extraction
•
7B
•
Updated
•
6
domenicrosati/repnoise_0.001beta_attacked_3e-4
Text Generation
•
7B
•
Updated
•
9
•
1
domenicrosati/repnoise_0.001_beta
Text Generation
•
7B
•
Updated
•
10
•
1
domenicrosati/repremove
Text Generation
•
7B
•
Updated
•
6
domenicrosati/representationremoval
Updated
domenicrosati/security_vectors_meta-llama_Llama-2-7b-chat-hf_8e-5_10k
Updated
domenicrosati/security_vectors_meta-llama_Llama-2-7b-chat-hf_3e-5_1k
Updated
domenicrosati/freeze_layers_ten_twenty_meta-llama_Llama-2-7b-chat-hf_minimality-mmd_defence_steps_10000
Text Generation
•
7B
•
Updated
•
6
domenicrosati/freeze_layers_lm_head_4_meta-llama_Llama-2-7b-chat-hf_adversarial_loss_defence_steps_10000
Text Generation
•
7B
•
Updated
•
6
domenicrosati/additional_models_Qwen_Qwen1.5-0.5B-Chat_minimality-mmd_defence_steps_10000
Text Generation
•
0.5B
•
Updated
•
6
domenicrosati/ablation_additional_minimality-mmd_defence_steps_1000
Text Generation
•
7B
•
Updated
•
7
domenicrosati/rep_noise_attacked_8e-5_10k
Feature Extraction
•
7B
•
Updated
•
5
domenicrosati/mxbai-rerank-xsmall-v1-onnx-optimized
Text Classification
•
Updated
•
6
domenicrosati/domenicrosati
Updated
domenicrosati/mxbai-rerank-xsmall-v1
Updated