yuniaXian / ppo_llm_DeepSpeed
Customized llm PPO (reinforcement learning) pipeline with deepSpeed. For Amex external usage. Training reward model, actor-critic models with referenced supervised fine-tuned model
☆1Updated 11 months ago
Alternatives and similar repositories for ppo_llm_DeepSpeed:
Users that are interested in ppo_llm_DeepSpeed are comparing it to the libraries listed below
- Collection of llm_langchain_projects: Autolabelling, Search and Indexing☆4Updated 8 months ago
- Implement of Knowledge graph to text model. Integrated with Fairseq (Meta Fair research library))☆2Updated 11 months ago
- extension of SMx crypto support for go standard lib☆2Updated last year
- 💬 Customized rasa chatbot framework based on llm to automate text- and voice-based conversations☆1Updated 11 months ago
- DEX platform - Zuniswap☆3Updated 11 months ago
- Pick Photo from iPhone Photos Library.☆4Updated 3 years ago
- ☆1Updated 10 months ago
- Full Stack Lottery Web Application☆3Updated last week
- find channel admin count☆21Updated 7 years ago
- ☆3Updated 8 months ago
- Dumps of Blackswipe☆26Updated 9 months ago
- valpapers repo☆4Updated 10 months ago
- Typescript command handler☆22Updated 11 months ago
- Free WordPress Plugin: A feet and inches calculator helps with math problems. Add feet and inches, subtract, multiply, or divide them wit…☆20Updated 8 months ago