← Trending
Tangerine Index lists products launched since ChatGPT and people's reactions to them.
xtuner
github.com
A Next-Generation Training Engine Built for Ultra-Large MoE Models
Open source
Reactions (1)
Similar products
by description similarity
We trained an MoE LLM built for developer tasks
Introducing Interfaze Hybrid Architecture: A unified transformer and DNN architecture that shares the same vector space and context window, allowing for seamless switching between modalities and specialized tasks.
- Hacker News
- 5 pts
- GitHub
- No reaction
Model Training Memory Simulator
Zhéyuán Chén's homepage
- Hacker News
- 10 pts
- GitHub
- No reaction
Yi
A series of large language models trained from scratch by developers @01-ai
- Hacker News
- No reaction
- GitHub
- 7,833 stars
verl
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
- Hacker News
- No reaction
- GitHub
- 24,162 stars
BELLE
BELLE: Be Everyone's Large Language model Engine(开源中文对话大模型)
- Hacker News
- No reaction
- GitHub
- 8,261 stars