Instructions to use beyoru/Ops-I with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beyoru/Ops-I with Transformers:

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

pipe = pipeline("text-generation", model="beyoru/Ops-I")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("beyoru/Ops-I")
model = AutoModelForMultimodalLM.from_pretrained("beyoru/Ops-I", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use beyoru/Ops-I with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "beyoru/Ops-I"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beyoru/Ops-I",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/beyoru/Ops-I

SGLang

How to use beyoru/Ops-I 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 "beyoru/Ops-I" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beyoru/Ops-I",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "beyoru/Ops-I" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beyoru/Ops-I",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use beyoru/Ops-I with Docker Model Runner:
```
docker model run hf.co/beyoru/Ops-I
```

beyoru commited on Aug 1

Commit

a30ce4b

verified ·

1 Parent(s): 798715f

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -5

README.md CHANGED Viewed

@@ -54,11 +54,6 @@ operations, sales, support) that holds up across long multi-step tool episodes.
 | gemma-4-31B-it (thinking on) | 10.17% | 61 | 41.64% | 2.15 h |
 | Qwen3.6-27B (base) | 9.67% | 58 | 46.00% | 1.95 h |
-**Read this honestly:** at n=600 one task is worth 0.17 points, so Ops-I, Gemma 4 and the
-base model sit within three tasks of each other — that spread is noise, not a ranking.
-What the numbers *do* support is that Ops-I is at least not worse than its base while
-being the fastest of the tuned models, and that it beats Opera by 10 tasks.
 For scale, the reference models in the upstream README (run at their highest reasoning
 effort) land at Claude Opus 4.8 30.33%, GPT-5.6 Sol 29.17%, GLM 5.2 20.33%,
 Gemini 3.5 Flash 14.83%.

 | gemma-4-31B-it (thinking on) | 10.17% | 61 | 41.64% | 2.15 h |
 | Qwen3.6-27B (base) | 9.67% | 58 | 46.00% | 1.95 h |
 For scale, the reference models in the upstream README (run at their highest reasoning
 effort) land at Claude Opus 4.8 30.33%, GPT-5.6 Sol 29.17%, GLM 5.2 20.33%,
 Gemini 3.5 Flash 14.83%.