Instructions to use CardinalOperations/ORLM-LLaMA-3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CardinalOperations/ORLM-LLaMA-3-8B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="CardinalOperations/ORLM-LLaMA-3-8B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CardinalOperations/ORLM-LLaMA-3-8B")
model = AutoModelForCausalLM.from_pretrained("CardinalOperations/ORLM-LLaMA-3-8B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CardinalOperations/ORLM-LLaMA-3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CardinalOperations/ORLM-LLaMA-3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CardinalOperations/ORLM-LLaMA-3-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CardinalOperations/ORLM-LLaMA-3-8B

SGLang

How to use CardinalOperations/ORLM-LLaMA-3-8B 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 "CardinalOperations/ORLM-LLaMA-3-8B" \
    --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": "CardinalOperations/ORLM-LLaMA-3-8B",
		"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 "CardinalOperations/ORLM-LLaMA-3-8B" \
        --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": "CardinalOperations/ORLM-LLaMA-3-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CardinalOperations/ORLM-LLaMA-3-8B with Docker Model Runner:
```
docker model run hf.co/CardinalOperations/ORLM-LLaMA-3-8B
```

CyrilHuang commited on Apr 3, 2025

Commit

94fdc3c

verified ·

1 Parent(s): 1960f40

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -4

README.md CHANGED Viewed

@@ -133,10 +133,11 @@ Below is the comparison of performance on the NL4OPT, MAMO, and IndustryOR bench
 ## Citation
 ```bibtex
-@article{tang2024orlm,
-  title={ORLM: Training Large Language Models for Optimization Modeling},
-  author={Tang, Zhengyang and Huang, Chenyu and Zheng, Xin and Hu, Shixi and Wang, Zizhuo and Ge, Dongdong and Wang, Benyou},
-  journal={arXiv preprint arXiv:2405.17743},
   year={2024}
 }
 ```

 ## Citation
 ```bibtex
+@article{huang2024orlm,
+  title={ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling},
+  author={Huang, Chenyu and Tang, Zhengyang and Ge, Dongdong and Hu, Shixi and Jiang, Ruoqing and Wang, Benyou and Wang, Zizhuo and Zheng, Xin},
+  journal={arXiv e-prints},
+  pages={arXiv--2405},
   year={2024}
 }
 ```