Image-Text-to-Text
PEFT
Safetensors
GGUF
English
lora
ocr
latex
math
Eval Results (legacy)
conversational
Instructions to use ogaude/glyphfix-math-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ogaude/glyphfix-math-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("lightonai/LightOnOCR-3-4B") model = PeftModel.from_pretrained(base_model, "ogaude/glyphfix-math-lora") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ogaude/glyphfix-math-lora with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf ogaude/glyphfix-math-lora:Q8_0 # Run inference directly in the terminal: llama cli -hf ogaude/glyphfix-math-lora:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ogaude/glyphfix-math-lora:Q8_0 # Run inference directly in the terminal: llama cli -hf ogaude/glyphfix-math-lora:Q8_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf ogaude/glyphfix-math-lora:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf ogaude/glyphfix-math-lora:Q8_0
Use Docker
docker model run hf.co/ogaude/glyphfix-math-lora:Q8_0
- Llama new
- LM Studio
- Jan
- vLLM
How to use ogaude/glyphfix-math-lora with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ogaude/glyphfix-math-lora" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ogaude/glyphfix-math-lora", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/ogaude/glyphfix-math-lora:Q8_0
- Ollama
How to use ogaude/glyphfix-math-lora with Ollama:
ollama run hf.co/ogaude/glyphfix-math-lora:Q8_0
- Unsloth Desktop
- Pi
How to use ogaude/glyphfix-math-lora with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ogaude/glyphfix-math-lora:Q8_0
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ogaude/glyphfix-math-lora:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ogaude/glyphfix-math-lora with Docker Model Runner:
docker model run hf.co/ogaude/glyphfix-math-lora:Q8_0
- Lemonade
How to use ogaude/glyphfix-math-lora with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ogaude/glyphfix-math-lora:Q8_0
Run and chat with the model
lemonade run user.glyphfix-math-lora-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use ogaude/glyphfix-math-lora with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ogaude/glyphfix-math-lora:Q8_0
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default ogaude/glyphfix-math-lora:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ogaude/glyphfix-math-lora with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ogaude/glyphfix-math-lora:Q8_0
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "ogaude/glyphfix-math-lora:Q8_0" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download assets/examples.json from ogaude/glyphfix-math-lora: direct link, hf CLI and curl.
- Browser
- Download file 2.71 kB
-
https://huggingface.co/ogaude/glyphfix-math-lora/resolve/main/assets/examples.json
- Command line
-
hf download hf://ogaude/glyphfix-math-lora/assets/examples.json
-
curl -L -o examples.json https://huggingface.co/ogaude/glyphfix-math-lora/resolve/main/assets/examples.json
2.71 kB
| [ | |
| { | |
| "base_correct": false, | |
| "class": "prime_l", | |
| "file": "example_1_prime_l.png", | |
| "id": "8424e5e5e48206f9", | |
| "note": "The base model made two errors: it read the triple prime as the Roman numeral III and dropped the minus on x_c; this model got both right.", | |
| "source": { | |
| "arxiv_id": "2408.10186", | |
| "arxiv_url": "https://arxiv.org/abs/2408.10186v3", | |
| "authors": [ | |
| "Hindy Drillick", | |
| "Levi Haunschmid-Sibitz" | |
| ], | |
| "license_spdx": "CC-BY-4.0", | |
| "license_uri": "http://creativecommons.org/licenses/by/4.0/", | |
| "title": "The stochastic six-vertex model speed process" | |
| }, | |
| "tuned_correct": true | |
| }, | |
| { | |
| "base_correct": false, | |
| "class": "decoration", | |
| "file": "example_2_decoration.png", | |
| "id": "0bfbeba7077c27ed", | |
| "note": "The base model lost the sans-serif style of A and B; this model kept it.", | |
| "source": { | |
| "arxiv_id": "2601.20152", | |
| "arxiv_url": "https://arxiv.org/abs/2601.20152v3", | |
| "authors": [ | |
| "Chen Cheng", | |
| "Rina Foygel Barber" | |
| ], | |
| "license_spdx": "CC-BY-4.0", | |
| "license_uri": "http://creativecommons.org/licenses/by/4.0/", | |
| "title": "Concentration Inequalities for Exchangeable Tensors and Matrix-valued Data" | |
| }, | |
| "tuned_correct": true | |
| }, | |
| { | |
| "base_correct": false, | |
| "class": "greek_latin", | |
| "file": "example_3_greek_latin.png", | |
| "id": "18395b29fe0f19ef", | |
| "note": "The base model read the Greek letter chi as the Latin x; this model read it correctly.", | |
| "source": { | |
| "arxiv_id": "2510.20320", | |
| "arxiv_url": "https://arxiv.org/abs/2510.20320v2", | |
| "authors": [ | |
| "Hanbing Fang", | |
| "Yu Li" | |
| ], | |
| "license_spdx": "CC0-1.0", | |
| "license_uri": "http://creativecommons.org/publicdomain/zero/1.0/", | |
| "title": "Strong uniqueness of tangent flows at cylindrical singularities in Ricci flow" | |
| }, | |
| "tuned_correct": true | |
| }, | |
| { | |
| "base_correct": false, | |
| "class": "decoration", | |
| "file": "example_4_decoration.png", | |
| "id": "01d56f4f68d6d327", | |
| "note": "A miss: both models lose the bold on the Greek letter (the reference is `\\boldsymbol{\\theta}`).", | |
| "source": { | |
| "arxiv_id": "2606.29349", | |
| "arxiv_url": "https://arxiv.org/abs/2606.29349v2", | |
| "authors": [ | |
| "Minjae Kim", | |
| "Jaehwan Jeong", | |
| "Seulki Lee", | |
| "Jaemin Kim" | |
| ], | |
| "license_spdx": "CC-BY-4.0", | |
| "license_uri": "http://creativecommons.org/licenses/by/4.0/", | |
| "title": "PDE-constrained optimization for virtual sensing in structural dynamics: Full-field displacement and force recovery from sparse sensors" | |
| }, | |
| "tuned_correct": false | |
| } | |
| ] | |