Spaces:
Sleeping
Sleeping
| title: ENIAD AI Assistant Chat | |
| emoji: 🎓 | |
| colorFrom: purple | |
| colorTo: blue | |
| sdk: gradio | |
| app_file: app.py | |
| pinned: true | |
| short_description: Interactive ENIAD AI Assistant (LLaMA-3.1-8B) | |
| # 🎓 ENIAD Assistant — Live Interactive Space | |
| ### 🤝 Official Multi-Author Engineering Project • ENIAD AI Lab (May 2025) | |
| Welcome to the interactive conversational interface for **ENIAD-ASSISTANT**, powered by a fine-tuned **LLaMA-3.1-8B** model. | |
| ### 👥 Engineering Team | |
| - **Abdellah ENNAJARI** — Lead AI & MLOps Engineer ([@abdennajari](https://huggingface.co/abdennajari) • [GitHub @ennajari](https://github.com/ennajari)) | |
| - **Ahmed OUKACHA** — AI Systems & Fine-Tuning Specialist ([@ahmed-ouka](https://huggingface.co/ahmed-ouka)) | |
| - **Oussama EL HADJI** — Full-Stack AI UI & SMA Multi-Agent Engineer ([HF @bosaj](https://huggingface.co/bosaj) • [GitHub @Bosaj](https://github.com/Bosaj)) | |
| - **Abdelilah OURTI** ([@abdelilahou](https://huggingface.co/abdelilahou)) — Vector DB & RAG Pipeline Engineer | |
| ### 🔗 Architecture & Associated Assets | |
| - **Original Model Checkpoint (May 2025):** [`ahmed-ouka/my-llama3.1-8B-with-lora-Eniad-Assistant`](https://huggingface.co/ahmed-ouka/my-llama3.1-8B-with-lora-Eniad-Assistant) | |
| - **Official Model Card:** [`bosaj/eniad-llama3.1-8b-assistant-lora`](https://huggingface.co/bosaj/eniad-llama3.1-8b-assistant-lora) | |
| - **Instruction Dataset:** [`bosaj/eniad-assistant-instruct-dataset`](https://huggingface.co/datasets/bosaj/eniad-assistant-instruct-dataset) | |
| - **GitHub Repository:** [`ennajari/ENIAD-ASSISTANT`](https://github.com/ennajari/ENIAD-ASSISTANT) | |
| ## 🏛️ The Complete ENIAD Chatbot Model Family (LLaMA & Qwen) | |
| The **ENIAD Chatbot ecosystem** consists of collaborative LLaMA & Qwen checkpoints, quantization profiles, and LoRA adapters engineered for our institutional assistant: | |
| | Model & Checkpoint | Base Architecture | Precision / Format | Target Environment & Use-Case | Verified Repository Link | | |
| | :--- | :--- | :--- | :--- | :--- | | |
| | **LLaMA-3.1-8B Assistant LoRA** | `meta-llama/Llama-3.1-8B` | 16-Bit PEFT LoRA (Rank 16, Alpha 32) | Primary institutional conversational assistant (Bilingual FR/EN) | [bosaj/eniad-llama3.1-8b-assistant-lora](https://huggingface.co/bosaj/eniad-llama3.1-8b-assistant-lora) | | |
| | **LLaMA-3-8B Merged 32-Bit** | `meta-llama/Meta-Llama-3-8B` | Full Float32 Merged Weights | Standalone backend inference server without runtime adapter loading | [ahmed-ouka/llama3-8b-eniad-merged-32bit](https://huggingface.co/ahmed-ouka/llama3-8b-eniad-merged-32bit) | | |
| | **LLaMA-3.1-8B Team Milestone** | `meta-llama/Llama-3.1-8B` | PEFT LoRA Sharded Safetensors | Original PFA milestone model checkpoint (May 2025 team release) | [ahmed-ouka/my-llama3.1-8B-with-lora-Eniad-Assistant](https://huggingface.co/ahmed-ouka/my-llama3.1-8B-with-lora-Eniad-Assistant) | | |
| | **Eniad LLaMA 8-Bit Quantized** | `meta-llama/Meta-Llama-3-8B` | 8-Bit `bitsandbytes` NF4/INT8 | High-efficiency local inference on edge GPUs (< 6GB VRAM) | [ahmed-ouka/Eniad-model-llama-Assistant](https://huggingface.co/ahmed-ouka/Eniad-model-llama-Assistant) | | |
| | **LLaMA-Factory 3.1 LoRA Adapter** | `meta-llama/Llama-3.1-8B` | Modular PEFT Adapter (~50MB) | Exported modular weights from the LLaMA-Factory training pipeline | [ahmed-ouka/llama-lora-adapter-eniad](https://huggingface.co/ahmed-ouka/llama-lora-adapter-eniad) | | |
| | **Qwen-2.5-1.5B ENIAD LoRA** | `Qwen/Qwen2.5-1.5B-Instruct` | 16-Bit PEFT LoRA (Compact) | Ultra-fast lightweight assistant for low-latency & edge devices (< 2GB VRAM) | [ahmed-ouka/lora-qwen-eniad](https://huggingface.co/ahmed-ouka/lora-qwen-eniad) | | |
| --- | |