domenicrosati/mxbai-rerank-xsmall-v1
Updated
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
Recent Activity
updated a model 17 days ago
domenicrosati/backdoored_smollm2 published a model 17 days ago
domenicrosati/backdoored_smollm2 new activity 9 months ago
openai/gpt-oss-20b:Why does it say 12B parameters when its 21B parameters?Organizations
domenicrosati/decoding_trust_mmd_immunization_minimality-mmd_lr_2e-5_alpha_2_beta_4_num_layers_6_epoch_4
Text Generation • 7B • Updated • 1
domenicrosati/decoding_trust_mmd_immunization_minimality-mmd_lr_2e-5_alpha_2_beta_4_num_layers_6_epoch_1
Text Generation • 7B • Updated • 1
domenicrosati/rep-noise_2e-5_batch_8_epoch_1
Text Generation • 7B • Updated • 4
domenicrosati/immunized-reverse-mmd
Updated
domenicrosati/decoding_trust_minimality_post_immunization_attack_8e5
Text Generation • 7B • Updated • 2
domenicrosati/decoding_trust_minimality_post_immunization_attack_6e5
Text Generation • 7B • Updated • 2
domenicrosati/decoding_trust_minimality_post_immunization_attack_3e5
Text Generation • 7B • Updated • 2
domenicrosati/decoding_trust_attack_8e5
Text Generation • 7B • Updated • 2
domenicrosati/lens-loss-minimality-l2_lr_2e-5_model_meta-llama_Llama-2-7b-chat-hf_batch_4_epoch_1_num_layers_6
Text Generation • 7B • Updated • 2
domenicrosati/decoding_trust_attack_6e5
Text Generation • 7B • Updated • 2
domenicrosati/decoding_trust_attack_3e5
Text Generation • 7B • Updated • 3
domenicrosati/adversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_4_num_layers_6_6e-5_1k
Text Generation • 7B • Updated • 2
domenicrosati/lens-loss-minimality_lr_2e-5_attack_meta-llama_Llama-2-7b-chat-hf_1_num_layers_6_6e-5_1k
Text Generation • 7B • Updated • 3
domenicrosati/adversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_4_num_layers_6_3e-5_1k
Text Generation • 7B • Updated • 3
domenicrosati/lens-loss-minimality_lr_2e-5_attack_meta-llama_Llama-2-7b-chat-hf_1_num_layers_6_3e-5_1k
Text Generation • 7B • Updated • 2
domenicrosati/adversarial_loss_lr_1e-5_model_meta-llama_Llama-2-7b-chat-hf_batch_4_epoch_4_num_layers_6
Text Generation • 7B • Updated • 2
domenicrosati/lens-loss-minimality_lr_2e-5_model_meta-llama_Llama-2-7b-chat-hf_batch_4_epoch_1_num_layers_6
Text Generation • 7B • Updated • 2
domenicrosati/lens-loss-minimality_lr_1e-5_model_meta-llama_Llama-2-7b-chat-hf_batch_4_epoch_1_num_layers_6
Text Generation • 7B • Updated • 2
domenicrosati/beavertails_attack_meta-llama_Llama-2-7b-chat-hf_3e-5_1k
Text Generation • 7B • Updated • 4
domenicrosati/adversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_4_num_layers_6_8e-5_1k
Text Generation • 7B • Updated • 3
domenicrosati/deberta-v3-xsmall-beavertails-harmful-qa-classifier
Text Classification • 70.8M • Updated • 481
domenicrosati/adversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_masked_4_6e-5_1k
Text Generation • 7B • Updated • 2
domenicrosati/adversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_masked_4_3e-5_1k
Text Generation • 7B • Updated • 3
domenicrosati/lens-loss-minimality_lr_2e-5_attack_meta-llama_Llama-2-7b-chat-hf_1_num_layers_24_8e-5_10k
Text Generation • 7B • Updated • 4
domenicrosati/lens-loss-minimality_lr_2e-5_attack_meta-llama_Llama-2-7b-chat-hf_1_num_layers_24_3e-5_1k
Text Generation • 7B • Updated • 2
domenicrosati/lens-loss-minimality_lr_2e-5_model_meta-llama_Llama-2-7b-chat-hf_batch_4_epoch_1_num_layers_24
Text Generation • 7B • Updated • 3
domenicrosati/lens-loss-minimality_lr_2e-5_attack_meta-llama_Llama-2-7b-chat-hf_1_num_layers_32_8e-5_10k
Text Generation • 7B • Updated • 2
domenicrosati/lens-loss-minimality_lr_2e-5_attack_meta-llama_Llama-2-7b-chat-hf_1_num_layers_32_3e-5_1k
Text Generation • 7B • Updated • 2
domenicrosati/lens-loss-minimality_lr_2e-5_model_meta-llama_Llama-2-7b-chat-hf_batch_4_epoch_1_num_layers_32
Text Generation • 7B • Updated • 2