VibeVoice is a community-maintained fork for expressive, longform conversational speech synthesis.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs with zero-code CLI and Web UI.
CogView4 is a text-to-image generation model from THUDM, along with its variants, focusing on improving image generation quality.
生成模型 tokenizer训练，模型初始化，模型预训练，指令微调。llama，creek
MAP-NEO is a fully open-sourced Large Language Model with state-of-the-art performance for diverse research applications.
