Text Generation
Transformers
Safetensors
English
Chinese
qwen3_5
image-text-to-text
apus-openjev
decision-model
structured-output
bf16
conversational
Instructions to use apus-ailab/APUS-OpenJev-v1-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use apus-ailab/APUS-OpenJev-v1-9B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="apus-ailab/APUS-OpenJev-v1-9B") 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)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("apus-ailab/APUS-OpenJev-v1-9B") model = AutoModelForMultimodalLM.from_pretrained("apus-ailab/APUS-OpenJev-v1-9B", 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=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use apus-ailab/APUS-OpenJev-v1-9B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "apus-ailab/APUS-OpenJev-v1-9B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "apus-ailab/APUS-OpenJev-v1-9B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/apus-ailab/APUS-OpenJev-v1-9B
- SGLang
How to use apus-ailab/APUS-OpenJev-v1-9B 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 "apus-ailab/APUS-OpenJev-v1-9B" \ --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": "apus-ailab/APUS-OpenJev-v1-9B", "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 "apus-ailab/APUS-OpenJev-v1-9B" \ --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": "apus-ailab/APUS-OpenJev-v1-9B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use apus-ailab/APUS-OpenJev-v1-9B with Docker Model Runner:
docker model run hf.co/apus-ailab/APUS-OpenJev-v1-9B
Download examples.py from apus-ailab/APUS-OpenJev-v1-9B: direct link, hf CLI and curl.
- Browser
- Download file 2.33 kB
-
https://huggingface.co/apus-ailab/APUS-OpenJev-v1-9B/resolve/9dd2482d4c282968e7841f31d5f6ee8f19b77fe0/examples.py
- Command line
-
hf download hf://apus-ailab/APUS-OpenJev-v1-9B@9dd2482d4c282968e7841f31d5f6ee8f19b77fe0/examples.py
-
curl -L -o examples.py https://huggingface.co/apus-ailab/APUS-OpenJev-v1-9B/resolve/9dd2482d4c282968e7841f31d5f6ee8f19b77fe0/examples.py
2.33 kB
| """Run against a local merged HF snapshot; no project-local dependencies.""" | |
| import argparse | |
| import json | |
| from openjet_runtime import OpenJet | |
| def decision_examples(): | |
| binary = { | |
| "id": "example-binary", | |
| "group_id": "example-binary", | |
| "primitive": "choice", | |
| "state": "Order 731 has been delivered. The customer's message says thank you.", | |
| "instructions": "Select the appropriate next workflow action.", | |
| "criteria": [ | |
| {"id": "close", "description": "Close the resolved support ticket."}, | |
| {"id": "refund", "description": "Refund an undelivered order."}, | |
| ], | |
| } | |
| browser = { | |
| "id": "example-browser", | |
| "group_id": "example-browser", | |
| "primitive": "choice", | |
| "state": "A settings page has 16 visible buttons labeled Page 1 through Page 16.", | |
| "instructions": "Navigate to Page 12 by choosing its matching button.", | |
| "criteria": [ | |
| {"id": f"click-{i}", "description": f"Click the Page {i} button."} | |
| for i in range(1, 17) | |
| ], | |
| } | |
| return binary, browser | |
| def main(): | |
| parser = argparse.ArgumentParser() | |
| parser.add_argument("model", help="Local merged snapshot directory") | |
| parser.add_argument("--device", default="cuda:0") | |
| parser.add_argument("--dtype", choices=["float32", "bfloat16"], default="bfloat16") | |
| parser.add_argument("--effort", choices=["low", "high", "both"], default="both") | |
| parser.add_argument( | |
| "--text", action="store_true", help="Also run slow TYPE reference" | |
| ) | |
| args = parser.parse_args() | |
| runtime = OpenJet.from_pretrained(args.model, args.device, args.dtype) | |
| efforts = ("low", "high") if args.effort == "both" else (args.effort,) | |
| for effort in efforts: | |
| for request in decision_examples(): | |
| result = runtime.decide(request, effort) | |
| print(json.dumps({"example": request["id"], **result}, ensure_ascii=False)) | |
| if args.text: | |
| result = runtime.generate_text( | |
| "Return only the literal text to type into a search box for 'red shoes'.", | |
| effort=effort, | |
| max_new_tokens=32, | |
| ) | |
| print(json.dumps({"example": "browser-type", **result}, ensure_ascii=False)) | |
| if __name__ == "__main__": | |
| main() | |