lucidrains/deep-daze
Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network)
Language: Python
#artificial_intelligence #deep_learning #implicit_neural_representation #multi_modality #siren #text_to_image #transformers
Stars: 127 Issues: 5 Forks: 11
https://github.com/lucidrains/deep-daze

kyegomez/Sophia
Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.
Language: Python
#artificial_intelligence #chatgpt #deep_learning #multi_modality #neural_network #optimizer
Stars: 229 Issues: 11 Forks: 16
https://github.com/kyegomez/Sophia

NVlabs/Long-RL
Long-RL: Scaling RL to Long Sequences
Language: Python
#efficient_ai #large_language_models #long_sequence #multi_modality #reinforcement_learning #sequence_parallelism
Stars: 301 Issues: 2 Forks: 3
https://github.com/NVlabs/Long-RL

OpenMOSS/MOSS-TTS-Nano
MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and the OpenMOSS team. With only 0.1B parameters, it is designed for realtime speech generation, can run directly on CPU without a GPU, and keeps the deployment stack simple enough for local demos, web serving, and lightweight product integration.
Language: Python
#audio_tokenizer #chinese #english #multi_modality #multilingual #realtime #streaming_audio #tts #voice_clone
Stars: 855 Issues: 13 Forks: 78
https://github.com/OpenMOSS/MOSS-TTS-Nano