-
Matcha-TTS: A fast TTS architecture with conditional flow matching
Paper • 2309.03199 • Published • 14 -
E3 TTS: Easy End-to-End Diffusion-based Text to Speech
Paper • 2311.00945 • Published • 17 -
Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling
Paper • 2311.00430 • Published • 57 -
coqui/XTTS-v2
Text-to-Speech • Updated • 5.77M • 3.26k
Dr. Nathan Patrick Corbett MD
Thatscientist
AI & ML interests
Psychiatry, Basic Science (e.g. bench immunology and genetics), Medical Education, Gamification, AI, Ethics, Sociology of Disability and Inequality, Philosophy of Science and Medicine.
Organizations
None yet
Towards LLMs for grown-ups who need to read/write more than a couple of paragraphs.
-
tiiuae/falcon-180B
Text Generation • 180B • Updated • 146 • 1.15k -
tiiuae/falcon-180B-chat
Text Generation • 180B • Updated • 73 • 544 -
DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models
Paper • 2309.14509 • Published • 19 -
Effective Long-Context Scaling of Foundation Models
Paper • 2309.16039 • Published • 30
-
Safe RLHF: Safe Reinforcement Learning from Human Feedback
Paper • 2310.12773 • Published • 28 -
The Generative AI Paradox: "What It Can Create, It May Not Understand"
Paper • 2311.00059 • Published • 20 -
LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B
Paper • 2310.20624 • Published • 13 -
Moral Foundations of Large Language Models
Paper • 2310.15337 • Published • 1
-
Matcha-TTS: A fast TTS architecture with conditional flow matching
Paper • 2309.03199 • Published • 14 -
E3 TTS: Easy End-to-End Diffusion-based Text to Speech
Paper • 2311.00945 • Published • 17 -
Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling
Paper • 2311.00430 • Published • 57 -
coqui/XTTS-v2
Text-to-Speech • Updated • 5.77M • 3.26k
Towards LLMs for grown-ups who need to read/write more than a couple of paragraphs.
-
tiiuae/falcon-180B
Text Generation • 180B • Updated • 146 • 1.15k -
tiiuae/falcon-180B-chat
Text Generation • 180B • Updated • 73 • 544 -
DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models
Paper • 2309.14509 • Published • 19 -
Effective Long-Context Scaling of Foundation Models
Paper • 2309.16039 • Published • 30
-
Safe RLHF: Safe Reinforcement Learning from Human Feedback
Paper • 2310.12773 • Published • 28 -
The Generative AI Paradox: "What It Can Create, It May Not Understand"
Paper • 2311.00059 • Published • 20 -
LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B
Paper • 2310.20624 • Published • 13 -
Moral Foundations of Large Language Models
Paper • 2310.15337 • Published • 1