SpeechT5 Collection The SpeechT5 framework consists of a shared seq2seq and six modal-specific (speech/text) pre/post-nets that can address a few audio-related tasks. • 8 items • Updated Jul 11 • 21
Multimodal Models Collection Multimodal models with leading performance. • 14 items • Updated 11 days ago • 15
MelodyFlow Collection MelodyFlow: High Fidelity Text-Guided Music Generation and Editing via Single-Stage Flow Matching • 7 items • Updated 10 days ago • 13
LayerSkip Collection Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710 • 8 items • Updated 7 days ago • 39
Reward Bench Collection Datasets, spaces, and models for the reward model benchmark! • 5 items • Updated Sep 25 • 7
Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution Paper • 2312.06640 • Published Dec 11, 2023 • 46
Llama 3.2 3B & 1B GGUF Quants Collection Llama.cpp compatible quants for Llama 3.2 3B and 1B Instruct models. • 4 items • Updated Sep 26 • 45
Japanese Stable LM Collection Suite of LLMs focusing on Japanese usage • 15 items • Updated May 7 • 18