Pinned Loading

1. rlhf-from-scratch rlhf-from-scratch Public

   A theoretical and practical deep dive into Reinforcement Learning with Human Feedback and it’s applications in Large Language Models from scratch.

   Jupyter Notebook 116 12

2. piramid piramid Public

   All-in-one binary for distributed model inference, retrieval, and vector search

   Rust 12 2

3. llm-from-scratch llm-from-scratch Public

   A theoretical and practical deep dive into Large Language Models and their applications on Deep learning from scratch.

   Jupyter Notebook 13

4. SparkyAI SparkyAI Public

   Swarm of AI Agents that work together to answer student specific query, perform actions on their behalf and self improve over time following SOTA architectures and strategies for maximum scalability.

   Python 7 2

5. Decoy Decoy Public

   ML pipeline for anomaly detection with reverse social engineering voice agents

   Python 4

6. kaelum kaelum Public

   Bootstrapping test-time scaling for reasoning agents with online reward modeling and dynamic mixture-of-experts routing.

   Python 6