All the materials from our work: From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation
Lukas Edman
leukas
AI & ML interests
NLP, tokenization, pretraining, low-resource
Recent Activity
updated a collection 12 days ago
HIPPO updated a collection 12 days ago
HIPPO updated a collection 12 days ago
HIPPOOrganizations
BabyLM2024 models
The CUTE benchmark is an LLM benchmark, testing LLMs' understanding of orthography. Check out our github here: https://github.com/Leukas/cute
All the materials from our work: From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation
Collection of trained models for the paper: Are Character-level Translations Worth the Wait?
BabyLM2024 models
Final model for BabyLM 2023
The CUTE benchmark is an LLM benchmark, testing LLMs' understanding of orthography. Check out our github here: https://github.com/Leukas/cute