Skip to content
View MadrasLe's full-sized avatar

Block or report MadrasLe

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. JadeAgent JadeAgent Public

    Governed Python agent runtime with durable JGX state capsules, crash recovery, idempotent tool replay, graph/mesh execution, CLI inspection, and LangGraph benchmarks.

    Python 1 1

  2. aethermap aethermap Public

    Semantic analysis platform with UMAP/HDBSCAN clustering for data intelligence + 2-stage RAG (Retrieval→Reranking→Generation) with citations.

    JavaScript

  3. AlphaCheckers-Zero AlphaCheckers-Zero Public

    AlphaCheckers-Zero: Deep Reinforcement Learning engine trained to defeat Humans and LLMs (Llama 3 70b, kimi k2), while maintaining a solid draw against Minimax Depth 8.

    Python 4 1

  4. Automated-Stock-WorkflowGenAi Automated-Stock-WorkflowGenAi Public

    End-to-end GenAI pipeline used to generate (SDXL), upscale, and analyze (Florence-2) stock images. Automates prompt engineering with Llama 3 and metadata tagging for platforms like Dreamstime.

    Jupyter Notebook

  5. MGRrmsnorm MGRrmsnorm Public

    Optimized Fused RMSNorm implementation with CUDA. Features vectorized memory access (float4), warp-level reductions, and efficient backward pass for LLM training

    Python 1

  6. MTLM-Serie-Mini-Transformer-language-models MTLM-Serie-Mini-Transformer-language-models Public

    MTLM Series: A research collection of Small Language Models (<1B) trained from scratch. Investigating architectural efficiency via Progressive Growth (Layer Stacking) in PyTorch and extreme token s…

    Python 1 2