{"id":26529032,"url":"https://github.com/codewitheshayoutube/acemed_ai","last_synced_at":"2026-04-17T05:31:44.493Z","repository":{"id":283933625,"uuid":"949397928","full_name":"codewithEshaYoutube/AceMed_AI","owner":"codewithEshaYoutube","description":null,"archived":false,"fork":false,"pushed_at":"2025-05-08T09:08:04.000Z","size":20085,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-08T10:24:07.884Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/codewithEshaYoutube.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-03-16T11:22:28.000Z","updated_at":"2025-05-08T09:08:08.000Z","dependencies_parsed_at":"2025-04-30T11:47:52.417Z","dependency_job_id":null,"html_url":"https://github.com/codewithEshaYoutube/AceMed_AI","commit_stats":null,"previous_names":["codewitheshayoutube/acemed_ai"],"tags_count":0,"template":false,"template_full_name":"streamlit/chatbot-template","purl":"pkg:github/codewithEshaYoutube/AceMed_AI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithEshaYoutube%2FAceMed_AI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithEshaYoutube%2FAceMed_AI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithEshaYoutube%2FAceMed_AI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithEshaYoutube%2FAceMed_AI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/codewithEshaYoutube","download_url":"https://codeload.github.com/codewithEshaYoutube/AceMed_AI/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codewithEshaYoutube%2FAceMed_AI/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31916751,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-16T18:22:33.417Z","status":"online","status_checked_at":"2026-04-17T02:00:06.879Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-03-21T16:28:44.945Z","updated_at":"2026-04-17T05:31:44.487Z","avatar_url":"https://github.com/codewithEshaYoutube.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AceMed AI 🇵🇰 \n\u003cdiv style=\"display: flex; justify-content: center;\"\u003e\n  \u003cimg src=\"Assets/Images/page-logo.png\" width=\"200\" alt=\"AceMed AI Logo\"/\u003e\n\u003c/div\u003e \nAI-powered MDCAT preparation platform tailored to PTB/Federal board syllabus using LLaMA-based fine-tuned models.\n\n---\n\n## 🖥️ Landing Page\n\n![Landing Page](/landing_page.jpg)\n\n### AceMed AI — Pakistan’s AI-Powered MDCAT Preparation Platform\n\n**Crack the MDCAT — Score Higher with AI Precision**\n\nAceMed AI is trained on exact FSC Federal, PTB, and provincial board books, offering precise, personalized preparation powered by advanced AI.\n\n👉 [Start Free Trial](https://acemed-ai.streamlit.app/)  \n👉 [Learn More](https://acemed-ai.streamlit.app/)\n\n---\n\n## 🌐 Navigation\n\n- Home  \n- About Us  \n- Features  \n- Pricing  \n- FAQs  \n- **Login | Register**\n\n---\n\n## 🎯 Key Highlights\n\n### Why AceMed AI?\n\nAceMed AI merges technology with education to create a personalized and efficient MDCAT prep experience. It replaces costly coaching centers with smart, adaptive tools, empowering students to:\n\n- Learn at their own pace\n- Focus on weak areas\n- Practice with real-time AI feedback\n\n**Mission:** To make high-quality MDCAT prep accessible, smart, and personalized through the power of AI.\n\n---\n\nAceMed AI is Pakistan’s first AI-powered MDCAT preparation assistant, trained on PTB and Federal Board books. It provides:\n\n- ✍️ Accurate, syllabus-based answers\n- 📊 Performance analytics dashboard\n- 🤖 Chatbot interface for MDCAT Q\u0026A\n- 📚 Curated MCQ banks\n- 🔍 Step-by-step numerical solvers\n- 🔄 Adaptive learning and feedback loops\n\n---\n\n## 🛠️ Technology Stack\n\n| Layer          | Tools \u0026 Frameworks                            |\n|----------------|------------------------------------------------|\n| **Frontend**   | Streamlit, HTML, TailwindCSS, React.js        |\n| **Backend**    | FastAPI, LangChain, Python, HuggingFace       |\n| **Database**   | MongoDB, Redis                                 |\n| **AI Models**  | LLaMA, LoRA Fine-Tuning, Transformers          |\n| **Infra**      | Google Colab Pro+, GitHub, Vercel              |\n\n---\n\n## 🔬 AI Model Fine-Tuning\n\nWe leverage the **LLaMA model**, fine-tuned using **LoRA (Low-Rank Adaptation)** to adapt the base language model to the **MDCAT domain**. This enables precise, context-aware responses aligned with FSc and PTB syllabi.\n\n👉 [Open Fine-Tuning Notebook in Colab](https://colab.research.google.com/drive/19h9IH47HhXx30C2gfd7Kr6GzJwB6-2-Y)\n\n### 📘 Fine-Tuning Overview\n\n| Component                 | Details                                                                 |\n|--------------------------|-------------------------------------------------------------------------|\n| **Base Model**           | Meta LLaMA (7B)                                                         |\n| **Fine-Tuning Method**   | LoRA (Low-Rank Adaptation)                                              |\n| **Data Used**            | Curated PTB + Federal Board textbook content + MDCAT MCQs              |\n| **Framework**            | 🤗 Hugging Face Transformers + PEFT                                     |\n| **Notebook**             | Google Colab for rapid iteration                                        |\n| **Training Objective**   | SFT (Supervised Fine-Tuning) on syllabus-aligned Q\u0026A                    |\n| **Epochs**               | 3–5 (adaptive based on validation loss)                                 |\n| **Optimization**         | AdamW optimizer, 5e-5 learning rate                                     |\n| **LoRA Ranks**           | r=8, alpha=16                                                           |\n| **Hardware Used**        | Google Colab Pro+ (A100 GPU)                                            |\n\n---\n\n## 🔄 Development Roadmap\n\nAceMed AI follows the **Agile Software Development Life Cycle (SDLC)** for rapid iteration, scalability, and user-focused features.\n\n### 📅 Phases\n\n1. **Research \u0026 Requirement Analysis**\n   - Aligning features with PMC syllabus \u0026 student feedback  \n   \n2. **Data Collection \u0026 Preprocessing**\n   - Structuring PTB/Federal board content and MCQs  \n   - Cleaning \u0026 labeling data for model training  \n\n3. **AI Model Development**\n   - Fine-tuning transformer-based models  \n   - Developing step-by-step numerical solvers  \n\n4. **System Development \u0026 Integration**\n   - Backend infrastructure + chatbot interface  \n   - Interactive dashboard for performance analytics  \n\n5. **Testing \u0026 Deployment**\n   - Unit \u0026 integration testing  \n   - Beta deployment for real-world usage  \n\n6. **User Feedback \u0026 Iteration**\n   - Feedback from students \u0026 educators  \n   - Feature refinement \u0026 model accuracy tuning  \n\n---\n\n## 💸 Pricing\n\n| Plan            | Price         | Features                                                                 |\n|-----------------|---------------|---------------------------------------------------------------------------|\n| 🎓 **Free**     | Rs 0/month    | Limited AI question generation, Basic analytics                          |\n| 🥇 **Gold**     | Rs 2500/month | Unlimited AI-generated questions, Detailed performance analytics, Support |\n| 👑 **Platinum** | Rs 5000/month | All Gold features, 1-on-1 mentoring, Exclusive MCQ banks                 |\n\n---\n\n## ❓ FAQs\n\n**Q: How is AceMed AI different from ChatGPT?**  \nA: It's trained specifically on MDCAT syllabus (Federal/PTB), ensuring relevant, accurate answers.\n\n**Q: Can AceMed AI improve my marks?**  \nA: Yes, through adaptive learning and targeted practice.\n\n**Q: Is past paper practice included?**  \nA: Yes, along with textbook references and explanations.\n\n**Q: How accurate are the answers?**  \nA: 95%+ based on internal testing. Manual reviews ongoing for edge cases.\n\n---\n\n## 🤝 Contribution Guidelines\n\nAceMed AI is open-source and welcomes contributions:\n\n1. Fork the repository  \n2. Create a feature branch  \n3. Commit your changes  \n4. Open a pull request  \n\n---\n\n## 📜 License \u0026 Links\n\n- **License**: MIT License  \n- **Website**: [AceMedAI.com](https://acemedai.com)  \n- **Contact**: support@acemed.ai |  \n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodewitheshayoutube%2Facemed_ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcodewitheshayoutube%2Facemed_ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodewitheshayoutube%2Facemed_ai/lists"}