Pinned Repositories
taming-transformers
Taming Transformers for High-Resolution Image Synthesis
trl
Train transformer language models with reinforcement learning.
llm-cxr
Official code for "LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation"
LaVIT
LaVIT: Empower the Large Language Model to Understand and Generate Visual Content
LLM-Dojo
欢迎来到 LLM-Dojo,这里是一个开源大模型学习场所,使用简洁且易阅读的代码构建模型训练框架(支持各种主流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩🎓👨🎓
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。
Faded1022's Repositories
Faded1022 doesn’t have any repository yet.