Add model card with Muqarnas branding

README.md

@@ -0,0 +1,134 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- thought-injection
+- rag
+- research
+- qwen
+- qrk-labs
+pipeline_tag: text-generation
+library_name: transformers
+base_model: Qwen/Qwen3-0.6B
+---
+
+<div align="center">
+
+<!-- Muqarnas Layers Logo -->
+<svg width="120" height="120" viewBox="0 0 64 64" fill="none" xmlns="http://www.w3.org/2000/svg">
+  <path d="M32 4 L4 32 L32 60 L60 32 Z" fill="none" stroke="#fafafa" stroke-width="0.6" opacity="0.3"/>
+  <path d="M32 10 L10 32 L32 54 L54 32 Z" fill="none" stroke="#fafafa" stroke-width="0.8" opacity="0.5"/>
+  <path d="M32 16 L16 32 L32 48 L48 32 Z" fill="none" stroke="#fafafa" stroke-width="1" opacity="0.7"/>
+  <path d="M32 22 L22 32 L32 42 L42 32 Z" fill="none" stroke="#fafafa" stroke-width="1.2"/>
+  <line x1="32" y1="4" x2="32" y2="22" stroke="#fafafa" stroke-width="0.5" opacity="0.4"/>
+  <line x1="60" y1="32" x2="42" y2="32" stroke="#fafafa" stroke-width="0.5" opacity="0.4"/>
+  <line x1="32" y1="60" x2="32" y2="42" stroke="#fafafa" stroke-width="0.5" opacity="0.4"/>
+  <line x1="4" y1="32" x2="22" y2="32" stroke="#fafafa" stroke-width="0.5" opacity="0.4"/>
+  <line x1="18" y1="18" x2="27" y2="27" stroke="#fafafa" stroke-width="0.5" opacity="0.3"/>
+  <line x1="46" y1="18" x2="37" y2="27" stroke="#fafafa" stroke-width="0.5" opacity="0.3"/>
+  <line x1="46" y1="46" x2="37" y2="37" stroke="#fafafa" stroke-width="0.5" opacity="0.3"/>
+  <line x1="18" y1="46" x2="27" y2="37" stroke="#fafafa" stroke-width="0.5" opacity="0.3"/>
+  <circle cx="32" cy="32" r="6" fill="none" stroke="#fafafa" stroke-width="0.8"/>
+  <circle cx="32" cy="32" r="2.5" fill="#fafafa"/>
+</svg>
+
+# akeel-cot
+
+**Research Prototype — Thought Injection for Grounded Reasoning**
+
+*A QRK Labs Research Model*
+
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Model Size](https://img.shields.io/badge/Parameters-0.6B-green.svg)]()
+
+</div>
+
+---
+
+## Overview
+
+**akeel-cot** is a research prototype exploring *Thought Injection* — a novel approach to retrieval-augmented generation where the model learns to request external knowledge mid-generation using explicit `<knowledge>` tags.
+
+Unlike traditional RAG (which retrieves before generation) or tool-use (which requires special training), Thought Injection allows the model to:
+
+1. **Reason** about what it knows and doesn't know
+2. **Request** specific information at the moment it's needed
+3. **Integrate** retrieved context seamlessly into its response
+
+This model is part of QRK Labs' research into human-centric AI systems.
+
+## How It Works
+
+```
+User: What is the capital of France?
+
+Model: <think>
+The user is asking about the capital of France. This is common knowledge.
+</think>
+
+The capital of France is Paris.
+```
+
+```
+User: What were QRK Labs' Q4 2025 revenues?
+
+Model: <think>
+This is asking for specific financial data I don't have. I need to retrieve this.
+<knowledge>QRK Labs Q4 2025 revenue financial results</knowledge>
+[Retrieved: QRK Labs reported Q4 2025 revenues of $2.3M, up 45% YoY...]
+</k_res>
+Based on the retrieved information, I can now answer.
+</think>
+
+QRK Labs reported Q4 2025 revenues of $2.3 million, representing a 45% year-over-year increase.
+```
+
+## Architecture
+
+- **Base Model:** Qwen3-0.6B
+- **Training:** Fine-tuned on thought injection reasoning traces
+- **Format:** ChatML with `<think>`, `<knowledge>`, and `</k_res>` tags
+
+## Intended Use
+
+This is a **research prototype** for exploring thought injection techniques. It is intended for:
+
+- Academic research on RAG and reasoning
+- Experimentation with knowledge-grounded generation
+- Understanding model uncertainty and knowledge boundaries
+
+**Not intended for production use.**
+
+## Limitations
+
+- Small model size (0.6B) limits general capabilities
+- Requires compatible inference infrastructure to inject retrieved content
+- Research prototype — not optimized for real-world deployment
+- May hallucinate or generate incorrect `<knowledge>` queries
+
+## Citation
+
+If you use this model in your research, please cite:
+
+```bibtex
+@misc{akeel-cot-2026,
+  author = {QRK Labs},
+  title = {Akeel-CoT: Thought Injection for Grounded Reasoning},
+  year = {2026},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/qrk-labs/akeel-cot}
+}
+```
+
+## Links
+
+- **QRK Labs:** [qrk.ng](https://qrk.ng)
+- **Research:** Coming soon
+- **Contact:** research@qrk.ng
+
+---
+
+<div align="center">
+<sub>Built with ☁️ by QRK Labs — Human-centric AI</sub>
+</div>