Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,104 @@
+---
+language:
+- en
+license: apache-2.0
+base_model: Qwen/Qwen3.5-2B
+tags:
+- latex
+- voice
+- accessibility
+- math
+- transcription
+- fine-tuned
+- gguf
+- quantized
+datasets:
+- kennethge123/latex-voice-dataset
+pipeline_tag: text-generation
+---
+
+# LaTeX Voice qwen3.5-2b (Q4_K_M GGUF)
+
+Fine-tuned **Qwen/Qwen3.5-2B** for voice-driven LaTeX transcription and editing, designed to help people with disabilities (fine motor disabilities, blindness, low vision) participate in STEM.
+
+This model converts natural language voice transcriptions into LaTeX notation, and can also edit existing LaTeX expressions based on voice commands. It handles messy speech-to-text output including homophones, filler words, truncations, and other real-world STT artifacts.
+
+Based on the [Phoenix](https://arxiv.org/abs/2508.07576) and [StereoMath](https://arxiv.org/abs/2501.01404) research papers.
+
+## Usage (llama.cpp)
+
+This repo contains a **Q4_K_M GGUF** file for use with [llama.cpp](https://github.com/ggerganov/llama.cpp). This is the recommended format for edge/laptop deployment with Vulkan or Metal acceleration.
+
+```bash
+# Download the GGUF file
+huggingface-cli download kennethge123/latex-voice-qwen3.5-2b-4bit qwen3.5-2b-Q4_K_M.gguf --local-dir .
+
+# Run with llama.cpp server
+./llama-server -m qwen3.5-2b-Q4_K_M.gguf -c 2048 -ngl 99
+```
+
+#### Example API call (with llama-server running)
+
+```bash
+curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
+  "messages": [
+    {"role": "system", "content": "Your goal is to transcribe what the user is saying into LaTeX. Output in <latex></latex> blocks."},
+    {"role": "user", "content": "User Instruction: the integral from zero to infinity of e to the negative x squared dx"}
+  ],
+  "max_tokens": 256,
+  "temperature": 0
+}'
+```
+
+For the full-precision transformers version, see [kennethge123/latex-voice-qwen3.5-2b](https://huggingface.co/kennethge123/latex-voice-qwen3.5-2b).
+
+## Evaluation Results
+
+| Configuration | Exact Match | First Match | N |
+|---|---|---|---|
+| Full precision (standard prompt) | 56.6% | 56.6% | 500 |
+| Full precision (varied prompts) | 50.2% | 50.2% | 500 |
+| 4-bit quantized (standard prompt) | 54.6% | 54.4% | 500 |
+| 4-bit quantized (varied prompts) | 48.4% | 48.4% | 500 |
+
+**Metrics:**
+- **Exact Match**: Predicted LaTeX (after normalization) matches any expected output exactly
+- **First Match**: First predicted output matches any expected output
+- **Standard prompt**: Uses the same system prompt as training
+- **Varied prompts**: Uses randomized system prompts to test generalization (more representative of real-world use)
+
+## Training Details
+
+- **Base model**: Qwen/Qwen3.5-2B
+- **Method**: LoRA fine-tuning (r=64, alpha=128)
+- **Dataset**: ~60K examples (30K transcription, 20K editing, 10K transforms)
+- **Data mix**: 55% clean voice, 45% messy/realistic STT artifacts
+- **Epochs**: 2-3
+- **Optimizer**: AdamW with cosine schedule
+- **Quantization**: Q4_K_M (GGUF) — converted from full-precision merged weights via llama.cpp
+
+## Intended Use
+
+This model is designed for:
+- Voice-to-LaTeX transcription for accessibility tools
+- Editing LaTeX expressions via natural language commands
+- Mathematical transformations (simplify, factor, differentiate, etc.)
+- Integration with voice-powered math workspaces like Phoenix
+
+## Limitations
+
+- Exact match is a strict metric; the model may produce mathematically equivalent but syntactically different LaTeX
+- Performance on very advanced (PhD-level) notation may be lower
+- The model works best with the context engine pattern from Phoenix
+- Voice transcription artifacts not in the training distribution may cause issues
+
+## Citation
+
+```bibtex
+@article{ge2025phoenix,
+  title={Phoenix: A Novel Context-Aware Voice-Powered Math Equation Workspace and Editor},
+  author={Ge, Kenneth and Paul, Ryan and Zhang, Priscilla and Seo, JooYoung},
+  journal={arXiv preprint arXiv:2508.07576},
+  year={2025}
+}
+```