Skip to content
View BilalAhmadSami's full-sized avatar
  • London, United Kingdom

Block or report BilalAhmadSami

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. Medical-RAG-Chatbot Medical-RAG-Chatbot Public

    Medical RAG chatbot answering diabetic retinopathy questions with cited sources, built with LangChain, ChromaDB, sentence-transformers, and Llama 3.3 70B (Groq). Deployed on HuggingFace Spaces.

    Python

  2. Mental-Health-Text-Classification-QLoRA Mental-Health-Text-Classification-QLoRA Public

    QLoRA fine-tuning of Phi-3 Mini for 3-class mental-health text classification (Normal/Depression/Stress); macro-F1 0.49→0.93. Built with HuggingFace PEFT, bitsandbytes, and Transformers. Research/e…

    Python

  3. Diabetic-Retinopathy-Grading Diabetic-Retinopathy-Grading Public

    Parallel EfficientNetB4 + Swin Transformer fusion for ordinal diabetic retinopathy grading using CORN loss - Test QWK 0.8077. Live demo on Hugging Face.

    Python

  4. Fine-Grained-Image-Classification Fine-Grained-Image-Classification Public

    Systematic hyperparameter tuning for fine-grained knife image classification across 543 categories — benchmarking EfficientNet-B0, ConvNeXt-Tiny, and Swin Transformer with PyTorch. Best result: Con…

    Shell

  5. Isolated-Word-Recognition-HMM Isolated-Word-Recognition-HMM Public

    Isolated word recognition over an 11-word vocabulary using Hidden Markov Models built from scratch in NumPy — MFCC features, Baum-Welch EM training, Viterbi decoding

    Python

  6. Content-Based-Image-Retrieval Content-Based-Image-Retrieval Public

    MATLAB implementation of 6 content-based image retrieval (CBIR) descriptors - colour histograms, spatial grids, edge texture, and PCA - evaluated with Precision-Recall on the MSRC dataset.