Instructions to use ogaude/glyphfix-math-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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

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"

glyphfix-math-lora / assets /chart_flips.svg

ogaude

Add files using upload-large-folder tool

ba4c12a verified 17 days ago

preview code

Raw History Blame Contribute Delete

4.84 kB

<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 760 464" width="760" height="464" role="img" aria-labelledby="t d">
<title id="t">Crop by crop: what changed</title>
<desc id="d">Right with both: 1081; Wrong with the base model, right with this model: 672; Right with the base model, wrong with this model: 64; Wrong with both: 871</desc>
<style>
svg{font-family:system-ui, -apple-system, 'Segoe UI', Roboto, sans-serif}
.bg{fill:#fcfcfb} .ink{fill:#0b0b0b} .sub{fill:#52514e} .grid{stroke:#d9d8d4;stroke-width:1}
.base{fill:#eb6834} .tuned{fill:#2a78d6} .box{fill:#f1f0ec;stroke:#d9d8d4} .arrow{stroke:#52514e;fill:none;stroke-width:2}
.good{fill:#2a78d6} .bad{fill:#eb6834} .neutral{fill:#b9b8b2} .mid{fill:#8f8e88}
@media (prefers-color-scheme:dark){
.bg{fill:#1a1a19} .ink{fill:#f0efec} .sub{fill:#c3c2b7} .grid{stroke:#3a3a38}
.base{fill:#d95926} .tuned{fill:#3987e5} .box{fill:#262625;stroke:#3a3a38} .arrow{stroke:#c3c2b7}
.good{fill:#3987e5} .bad{fill:#d95926} .neutral{fill:#6b6a66} .mid{fill:#8f8e88}
}
</style>
<rect class="bg" width="760" height="464" rx="8"/>
<text x="24" y="34" class="ink" font-size="17" text-anchor="start" font-weight="600">Crop by crop: what changed</text>
<text x="24" y="56" class="sub" font-size="13" text-anchor="start" font-weight="400">All 2,688 benchmark crops, by whether each model rendered them identically to the paper</text>
<rect class="neutral" x="24.0" y="74" width="284.3" height="34" rx="3"/>
<text x="28.0" y="96" class="ink" font-size="13" text-anchor="start" font-weight="600">1,081</text>
<rect class="good" x="310.3" y="74" width="176.0" height="34" rx="3"/>
<text x="314.3363095238095" y="96" class="ink" font-size="13" text-anchor="start" font-weight="600">672</text>
<rect class="bad" x="488.3" y="74" width="15.0" height="34" rx="3"/>
<rect class="neutral" x="505.3" y="74" width="228.7" height="34" rx="3"/>
<text x="509.2886904761905" y="96" class="ink" font-size="13" text-anchor="start" font-weight="600">871</text>
<rect class="neutral" x="24" y="122" width="12" height="12" rx="2"/>
<text x="44" y="132" class="sub" font-size="13" text-anchor="start" font-weight="400">Right with both: 1,081</text>
<rect class="good" x="24" y="144" width="12" height="12" rx="2"/>
<text x="44" y="154" class="sub" font-size="13" text-anchor="start" font-weight="400">Wrong with the base model, right with this model: 672</text>
<rect class="bad" x="24" y="166" width="12" height="12" rx="2"/>
<text x="44" y="176" class="sub" font-size="13" text-anchor="start" font-weight="400">Right with the base model, wrong with this model: 64</text>
<rect class="neutral" x="24" y="188" width="12" height="12" rx="2"/>
<text x="44" y="198" class="sub" font-size="13" text-anchor="start" font-weight="400">Wrong with both: 871</text>
<text x="24" y="244" class="ink" font-size="14" text-anchor="start" font-weight="600">The 64 crops this model got wrong that the base model got right, by bucket</text>
<text x="214" y="276" class="ink" font-size="13" text-anchor="end" font-weight="400">content</text>
<rect class="bad" x="230" y="262" width="446.0" height="18" rx="3"/>
<text x="682.0" y="276" class="ink" font-size="12" text-anchor="start" font-weight="600">26</text>
<text x="214" y="304" class="ink" font-size="13" text-anchor="end" font-weight="400">layout / sizing</text>
<rect class="bad" x="230" y="290" width="343.1" height="18" rx="3"/>
<text x="579.0769230769231" y="304" class="ink" font-size="12" text-anchor="start" font-weight="600">20</text>
<text x="214" y="332" class="ink" font-size="13" text-anchor="end" font-weight="400">glyph classes</text>
<rect class="bad" x="230" y="318" width="171.5" height="18" rx="3"/>
<text x="407.53846153846155" y="332" class="ink" font-size="12" text-anchor="start" font-weight="600">10</text>
<text x="214" y="360" class="ink" font-size="13" text-anchor="end" font-weight="400">spacing</text>
<rect class="bad" x="230" y="346" width="85.8" height="18" rx="3"/>
<text x="321.7692307692308" y="360" class="ink" font-size="12" text-anchor="start" font-weight="600">5</text>
<text x="214" y="388" class="ink" font-size="13" text-anchor="end" font-weight="400">alignment wrapper</text>
<rect class="bad" x="230" y="374" width="34.3" height="18" rx="3"/>
<text x="270.3076923076923" y="388" class="ink" font-size="12" text-anchor="start" font-weight="600">2</text>
<text x="214" y="416" class="ink" font-size="13" text-anchor="end" font-weight="400">same text, render differs</text>
<rect class="bad" x="230" y="402" width="17.2" height="18" rx="3"/>
<text x="253.15384615384616" y="416" class="ink" font-size="12" text-anchor="start" font-weight="600">1</text>
<text x="24" y="450" class="sub" font-size="12" text-anchor="start" font-weight="400">Bucket of this model's wrong output. Buckets are a pattern heuristic, for reporting only.</text>
</svg>

	<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 760 464" width="760" height="464" role="img" aria-labelledby="t d">
	<title id="t">Crop by crop: what changed</title>
	<desc id="d">Right with both: 1081; Wrong with the base model, right with this model: 672; Right with the base model, wrong with this model: 64; Wrong with both: 871</desc>
	<style>
	svg{font-family:system-ui, -apple-system, 'Segoe UI', Roboto, sans-serif}
	.bg{fill:#fcfcfb} .ink{fill:#0b0b0b} .sub{fill:#52514e} .grid{stroke:#d9d8d4;stroke-width:1}
	.base{fill:#eb6834} .tuned{fill:#2a78d6} .box{fill:#f1f0ec;stroke:#d9d8d4} .arrow{stroke:#52514e;fill:none;stroke-width:2}
	.good{fill:#2a78d6} .bad{fill:#eb6834} .neutral{fill:#b9b8b2} .mid{fill:#8f8e88}
	@media (prefers-color-scheme:dark){
	.bg{fill:#1a1a19} .ink{fill:#f0efec} .sub{fill:#c3c2b7} .grid{stroke:#3a3a38}
	.base{fill:#d95926} .tuned{fill:#3987e5} .box{fill:#262625;stroke:#3a3a38} .arrow{stroke:#c3c2b7}
	.good{fill:#3987e5} .bad{fill:#d95926} .neutral{fill:#6b6a66} .mid{fill:#8f8e88}
	}
	</style>
	<rect class="bg" width="760" height="464" rx="8"/>
	<text x="24" y="34" class="ink" font-size="17" text-anchor="start" font-weight="600">Crop by crop: what changed</text>
	<text x="24" y="56" class="sub" font-size="13" text-anchor="start" font-weight="400">All 2,688 benchmark crops, by whether each model rendered them identically to the paper</text>
	<rect class="neutral" x="24.0" y="74" width="284.3" height="34" rx="3"/>
	<text x="28.0" y="96" class="ink" font-size="13" text-anchor="start" font-weight="600">1,081</text>
	<rect class="good" x="310.3" y="74" width="176.0" height="34" rx="3"/>
	<text x="314.3363095238095" y="96" class="ink" font-size="13" text-anchor="start" font-weight="600">672</text>
	<rect class="bad" x="488.3" y="74" width="15.0" height="34" rx="3"/>
	<rect class="neutral" x="505.3" y="74" width="228.7" height="34" rx="3"/>
	<text x="509.2886904761905" y="96" class="ink" font-size="13" text-anchor="start" font-weight="600">871</text>
	<rect class="neutral" x="24" y="122" width="12" height="12" rx="2"/>
	<text x="44" y="132" class="sub" font-size="13" text-anchor="start" font-weight="400">Right with both: 1,081</text>
	<rect class="good" x="24" y="144" width="12" height="12" rx="2"/>
	<text x="44" y="154" class="sub" font-size="13" text-anchor="start" font-weight="400">Wrong with the base model, right with this model: 672</text>
	<rect class="bad" x="24" y="166" width="12" height="12" rx="2"/>
	<text x="44" y="176" class="sub" font-size="13" text-anchor="start" font-weight="400">Right with the base model, wrong with this model: 64</text>
	<rect class="neutral" x="24" y="188" width="12" height="12" rx="2"/>
	<text x="44" y="198" class="sub" font-size="13" text-anchor="start" font-weight="400">Wrong with both: 871</text>
	<text x="24" y="244" class="ink" font-size="14" text-anchor="start" font-weight="600">The 64 crops this model got wrong that the base model got right, by bucket</text>
	<text x="214" y="276" class="ink" font-size="13" text-anchor="end" font-weight="400">content</text>
	<rect class="bad" x="230" y="262" width="446.0" height="18" rx="3"/>
	<text x="682.0" y="276" class="ink" font-size="12" text-anchor="start" font-weight="600">26</text>
	<text x="214" y="304" class="ink" font-size="13" text-anchor="end" font-weight="400">layout / sizing</text>
	<rect class="bad" x="230" y="290" width="343.1" height="18" rx="3"/>
	<text x="579.0769230769231" y="304" class="ink" font-size="12" text-anchor="start" font-weight="600">20</text>
	<text x="214" y="332" class="ink" font-size="13" text-anchor="end" font-weight="400">glyph classes</text>
	<rect class="bad" x="230" y="318" width="171.5" height="18" rx="3"/>
	<text x="407.53846153846155" y="332" class="ink" font-size="12" text-anchor="start" font-weight="600">10</text>
	<text x="214" y="360" class="ink" font-size="13" text-anchor="end" font-weight="400">spacing</text>
	<rect class="bad" x="230" y="346" width="85.8" height="18" rx="3"/>
	<text x="321.7692307692308" y="360" class="ink" font-size="12" text-anchor="start" font-weight="600">5</text>
	<text x="214" y="388" class="ink" font-size="13" text-anchor="end" font-weight="400">alignment wrapper</text>
	<rect class="bad" x="230" y="374" width="34.3" height="18" rx="3"/>
	<text x="270.3076923076923" y="388" class="ink" font-size="12" text-anchor="start" font-weight="600">2</text>
	<text x="214" y="416" class="ink" font-size="13" text-anchor="end" font-weight="400">same text, render differs</text>
	<rect class="bad" x="230" y="402" width="17.2" height="18" rx="3"/>
	<text x="253.15384615384616" y="416" class="ink" font-size="12" text-anchor="start" font-weight="600">1</text>
	<text x="24" y="450" class="sub" font-size="12" text-anchor="start" font-weight="400">Bucket of this model's wrong output. Buckets are a pattern heuristic, for reporting only.</text>
	</svg>