Pinned Loading

1. LLM-quest LLM-quest Public

   Verbose implementations of LLMs architectures, techniques and research papers from scratch. DeepSeek, Qwen3..., RLHF, MoE, Multimodal...

   Python 9

2. aaamlp-enhanced-pdf aaamlp-enhanced-pdf Public

   Approaching (Almost) Any Machine Learning Problem (AAAMLP) PDF from @abhishekkrthakur with outline, cover, notes

   Jupyter Notebook 1

3. GRPO-classic-RL GRPO-classic-RL Public

   Open-source implementation/adaptation of DeepSeek GRPO applied to Reinforcement Learning control problems. Example on LunarLander-V3.

   Jupyter Notebook

4. bdo-enhancing-model bdo-enhancing-model Public

   Probabilistic Modeling of Black Desert Online's Enhancement System. A proof of concept predicting outcomes to derive optimal profitability strategies.

   Jupyter Notebook

5. ffn-from-scratch ffn-from-scratch Public

   Feed Forward Neural Network (FFN) from Scratch. In pure Python and NumPy. One derivative at a time.

   Jupyter Notebook 1