Instructions to use ShunyaLab/OpenMath with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ShunyaLab/OpenMath with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ShunyaLab/OpenMath")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ShunyaLab/OpenMath", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ShunyaLab/OpenMath with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ShunyaLab/OpenMath" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ShunyaLab/OpenMath", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ShunyaLab/OpenMath
- SGLang
How to use ShunyaLab/OpenMath with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "ShunyaLab/OpenMath" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ShunyaLab/OpenMath", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "ShunyaLab/OpenMath" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ShunyaLab/OpenMath", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ShunyaLab/OpenMath with Docker Model Runner:
docker model run hf.co/ShunyaLab/OpenMath
Update README.md
Browse files
README.md
CHANGED
|
@@ -99,7 +99,9 @@ This project provides the fine-tuned adapter weights:
|
|
| 99 |
|
| 100 |
## Disclaimer
|
| 101 |
OpenMath is an educational/research project.
|
|
|
|
| 102 |
The fine-tuned model may produce incorrect, incomplete, or misleading answers.
|
|
|
|
| 103 |
Always verify solutions independently before using them for exams, assignments, or real-world decisions.
|
| 104 |
|
| 105 |
This project does **not** guarantee correctness and should not be used as a substitute for professional advice.
|
|
@@ -128,6 +130,7 @@ If you’d like to contribute:
|
|
| 128 |
|
| 129 |
## Note
|
| 130 |
OpenMath is a **fun and practical side project** built to explore **efficient fine-tuning (QLoRA)** and **math reasoning evaluation** on limited compute.
|
|
|
|
| 131 |
The goal is to learn, experiment, and share reproducible results — while keeping the code clean and open for community improvements.
|
| 132 |
|
| 133 |
---
|
|
|
|
| 99 |
|
| 100 |
## Disclaimer
|
| 101 |
OpenMath is an educational/research project.
|
| 102 |
+
|
| 103 |
The fine-tuned model may produce incorrect, incomplete, or misleading answers.
|
| 104 |
+
|
| 105 |
Always verify solutions independently before using them for exams, assignments, or real-world decisions.
|
| 106 |
|
| 107 |
This project does **not** guarantee correctness and should not be used as a substitute for professional advice.
|
|
|
|
| 130 |
|
| 131 |
## Note
|
| 132 |
OpenMath is a **fun and practical side project** built to explore **efficient fine-tuning (QLoRA)** and **math reasoning evaluation** on limited compute.
|
| 133 |
+
|
| 134 |
The goal is to learn, experiment, and share reproducible results — while keeping the code clean and open for community improvements.
|
| 135 |
|
| 136 |
---
|