Models
wemm-embedding
tencent/wemm-embedding
Tencent's family of universal multimodal embedding models, released in 2B, 4B and 9B sizes, mapping text, images, videos and visual documents into a shared retrieval space.
Topics
Related projects
MOSS-TTS4.3kAn open-source speech model family for long-form TTS, dialogue synthesis, voice design, and streaming speech.- MOSS-Audio701An open-source audio understanding model family for speech, environmental sound and music. The release provides 4B and 8B Instruct and Thinking weights for captioning, timestamped ASR, audio QA and reasoning.
anything-llm68.1kAn all-in-one self-hosted AI platform to chat with docs, run agents and manage models and users privately.
screenpipe22.4kA local-first app that continuously records screen and audio into searchable AI memory to recall work and power automations.
ms-swift16.1kA full-pipeline framework for fine-tuning, aligning, evaluating, and deploying hundreds of LLMs and multimodal models.
all-in-rag12.9kA comprehensive Chinese tutorial series teaching RAG end to end, from chunking and indexing to retrieval, evaluation, and projects.