Pinned Loading

1. MiniLM-L6-v2-with-nemotron-3-nano-RAG MiniLM-L6-v2-with-nemotron-3-nano-RAG Public

   Local RAG using Huggingface embedding model "MiniLM-L6-v2" with Ollama API to call Nemotron-3-Nano, a state of the art 30b MoE (mixture of experts) Large Language Model that uses a hybrid Mamba-Tra…

   Python

2. Lab-LLM-Proxy Lab-LLM-Proxy Public

   A secure Flask-based web proxy that provides authenticated access to local Ollama LLM instances through both a clean web interface and RESTful API. Features include password-protected access with b…

   Python

3. KMeansEMF-Multiplier KMeansEMF-Multiplier Public

   This project implements large-scale waveform generation, feature extraction, and clustering with GPU acceleration using CUDA via the RAPIDS suite (cuDF, cuML, cuPy). The system automatically falls …

   Python

4. Qwen-Fine-Tuning-Lab Qwen-Fine-Tuning-Lab Public

   A unified, configuration-driven pipeline for fine-tuning Qwen models on scientific datasets with automated evaluation

   Python