Elias Bassani's picture

11

Elias Bassani

AmenRa

·

https://amenra.github.io/eliasbassani

AI & ML interests

AI Safety, NLP, Information Retrieval, Neural Architectures

Recent Activity

new activity 2 days ago

nvidia/llama-3.1-nemoguard-8b-content-safety:Usage example

updated a Space 12 days ago

AmenRa/guardbench-leaderboard

published a Space 20 days ago

AmenRa/guardbench-leaderboard

View all activity

Organizations

AmenRa's activity

New activity in nvidia/llama-3.1-nemoguard-8b-content-safety 2 days ago

Usage example

#4 opened 2 days ago by

New activity in TrustAIRLab/in-the-wild-jailbreak-prompts 5 months ago

Enormous amount of duplicates

#3 opened 5 months ago by

New activity in meta-llama/Llama-Guard-3-1B 7 months ago

Missing tokenizer in example

#13 opened 7 months ago by

New activity in mlabonne/NeuralDaredevil-8B-abliterated 8 months ago

Missing license

#10 opened 8 months ago by

New activity in google/shieldgemma-2b 9 months ago

Checking multiple policy rules

#11 opened 9 months ago by

Policy rules definition

#10 opened 9 months ago by

New activity in instruction-pretrain/ft-instruction-synthesizer-collection 9 months ago

License

#3 opened 9 months ago by

New activity in nvidia/Aegis-AI-Content-Safety-Dataset-1.0 9 months ago

A few questions

#6 opened 11 months ago by

New activity in declare-lab/HarmfulQA 11 months ago

Inconsistent number of blue and red conversation

#2 opened 11 months ago by

New activity in NobodyExistsOnTheInternet/ToxicDPOqa 11 months ago

Data provenance

#2 opened 11 months ago by

New activity in lmsys/toxic-chat 11 months ago

Question about toxicity labels

#5 opened 11 months ago by

New activity in nvidia/Aegis-AI-Content-Safety-Dataset-1.0 11 months ago

A few questions

#6 opened 11 months ago by

A few questions

#6 opened 11 months ago by