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

7347643

verified ·

1 Parent(s): a30ce4b

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -2

README.md CHANGED Viewed

@@ -31,8 +31,7 @@ On the public 600-task [AutomationBench](https://github.com/zapier/AutomationBen
 (Zapier), Ops-I is the **strongest of four open-weight models** we measured, ahead of the
 Qwen3.6-27B base it was tuned from.
-**Use it if you need:** an open-weight backend for business automation (finance, HR,
-operations, sales, support) that holds up across long multi-step tool episodes.
 | | |
 |---|---|
@@ -157,6 +156,10 @@ print(r.choices[0].message.tool_calls)
 - Numbers were produced with SGLang 0.5.12. A vLLM baseline was not measured, so do not
   mix serving stacks when comparing.
 ## Citation
 Benchmark tasks, tools and assertions are Zapier's:

 (Zapier), Ops-I is the **strongest of four open-weight models** we measured, ahead of the
 Qwen3.6-27B base it was tuned from.
+**Use it if you need:** an open-weight backend for business automation that holds up across long multi-step tool episodes.
 | | |
 |---|---|
 - Numbers were produced with SGLang 0.5.12. A vLLM baseline was not measured, so do not
   mix serving stacks when comparing.
+# Limitaion
+**The model only take a few steps training because of LIMITATION gpu usage in our org**
 ## Citation
 Benchmark tasks, tools and assertions are Zapier's: