Castiel's starred repositories
GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Advances on Multimodal Large Language Models
lm-evaluation-harness
A framework for few-shot evaluation of language models.
awesome-RLHF
A curated list of reinforcement learning with human feedback resources (continually updated)
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型,实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。
data-juicer
A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据!
multimodal
TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.
Qwen-Audio
The official repo of Qwen-Audio (通义千问-Audio) chat & pretrained large audio language model proposed by Alibaba Cloud.
Multimodal-AND-Large-Language-Models
Paper list about multimodal and large language models, only used to record papers I read in the daily arxiv for personal needs.
sft_datasets
开源SFT数据集整理,随时补充
video-bgm-generation
Video Background Music Generation with Controllable Music Transformer (ACM MM 2021 Best Paper Award)