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

Libraries

How to use RichardErkhov/CardinalOperations_-_ORLM-LLaMA-3-8B-8bits with Transformers:

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

pipe = pipeline("text-generation", model="RichardErkhov/CardinalOperations_-_ORLM-LLaMA-3-8B-8bits")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichardErkhov/CardinalOperations_-_ORLM-LLaMA-3-8B-8bits")
model = AutoModelForCausalLM.from_pretrained("RichardErkhov/CardinalOperations_-_ORLM-LLaMA-3-8B-8bits", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RichardErkhov/CardinalOperations_-_ORLM-LLaMA-3-8B-8bits with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RichardErkhov/CardinalOperations_-_ORLM-LLaMA-3-8B-8bits

SGLang

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

Docker Model Runner
How to use RichardErkhov/CardinalOperations_-_ORLM-LLaMA-3-8B-8bits with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/CardinalOperations_-_ORLM-LLaMA-3-8B-8bits
```

RichardErkhov

nielsr HF Staff commited on Apr 8, 2025

Commit

4e47dc8

verified ·

1 Parent(s): 9d34326

Add missing metadata and links to ORLM-LLaMA-3-8B model card (#1)

Browse files

- Add missing metadata and links to ORLM-LLaMA-3-8B model card (98dd8f0a63a9008f2a814ef628e88682f386c5f4)

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +10 -5

README.md CHANGED Viewed

@@ -1,3 +1,9 @@
 Quantization made by Richard Erkhov.
 [Github](https://github.com/RichardErkhov)
@@ -18,14 +24,14 @@ Original model description:
 ---
 license: llama3
 ---
-see our paper in https://arxiv.org/abs/2405.17743
-github repo: https://github.com/Cardinal-Operations/ORLM
 ## Model Details
 LLaMA-3-8B-ORLM is fully fine-tuned on the OR-Instruct data and built with Meta [LLaMA-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) model.
-More training details can be seen at https://arxiv.org/abs/2405.17743
 ## Model Usage
@@ -168,5 +174,4 @@ Below is the comparison of performance on the NL4OPT, MAMO, and IndustryOR bench
 ```
 ## License
-The use of this model is governed by the [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](https://llama.meta.com/llama3/license/).

+---
+license: llama3
+pipeline_tag: text-generation
+library_name: transformers
+---
 Quantization made by Richard Erkhov.
 [Github](https://github.com/RichardErkhov)
 ---
 license: llama3
 ---
+This model is described in [ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling](https://huggingface.co/papers/2405.17743).
+Code: https://github.com/Cardinal-Operations/ORLM
 ## Model Details
 LLaMA-3-8B-ORLM is fully fine-tuned on the OR-Instruct data and built with Meta [LLaMA-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) model.
+More training details can be seen at [the paper](https://arxiv.org/abs/2405.17743).
 ## Model Usage
 ```
 ## License
+The use of this model is governed by the [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](https://llama.meta.com/llama3/license/).