wucong25/verl-recipe
A set of examples based on verl for end-to-end RL training recipes.
Repositories
wucong25/verl
verl: Volcano Engine Reinforcement Learning for LLMs
wucong25/RL_Memory_Estimator
Memory Estimator in RL
wucong25/verl-omni
Multimodal RL training framework for diffusion & omni models
wucong25/vllm-ascend
Community maintained hardware plugin for vLLM on Ascend
wucong25/Megatron-LM
Ongoing research training transformer models at scale
wucong25/verl-ascend-recipe
verl Ascend specific recipe
wucong25/lf-ml-compare-tools
wucong25/verl-data
wucong25/Megatron-Bridge
Training library for Megatron-based models with bi-directional Hugging Face conversion capability
wucong25/mbridge
Bridge Megatron-Core to Hugging Face/Reinforcement Learning
wucong25/LLaMA-Factory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
wucong25/emoji_spider_wechat
爬取热门表情包并通过微信展示
wucong25/BlockChain
黑马程序员 120天全栈区块链开发 开源教程
wucong25/SpringBoot-Learning
Spring Boot基础教程，Spring Boot 2.x版本连载中！！！