Image-Text-to-Text
Transformers
Safetensors
premonition_diffusion_gemma
vllm
diffusion-gemma
multimodal
audio
video
custom_code
conversational
Instructions to use prem-research/Premonition-Exp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prem-research/Premonition-Exp with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="prem-research/Premonition-Exp", trust_remote_code=True) 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 AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained("prem-research/Premonition-Exp", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use prem-research/Premonition-Exp with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "prem-research/Premonition-Exp" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prem-research/Premonition-Exp", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/prem-research/Premonition-Exp
- SGLang
How to use prem-research/Premonition-Exp 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 "prem-research/Premonition-Exp" \ --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": "prem-research/Premonition-Exp", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "prem-research/Premonition-Exp" \ --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": "prem-research/Premonition-Exp", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use prem-research/Premonition-Exp with Docker Model Runner:
docker model run hf.co/prem-research/Premonition-Exp
Download examples/decision.py from prem-research/Premonition-Exp: direct link, hf CLI and curl.
- Browser
- Download file 1.87 kB
-
https://huggingface.co/prem-research/Premonition-Exp/resolve/main/examples/decision.py
- Command line
-
hf download hf://prem-research/Premonition-Exp/examples/decision.py
-
curl -L -o decision.py https://huggingface.co/prem-research/Premonition-Exp/resolve/main/examples/decision.py
1.87 kB
| """Send the recorded fictional scenarios to a live Premonition decision server.""" | |
| import argparse | |
| import base64 | |
| import json | |
| from pathlib import Path | |
| import httpx | |
| def request(case, root): | |
| media = [] | |
| for name in case["files"]: | |
| path = root / "demo" / "assets" / name | |
| mime, kind = { | |
| ".png": ("image/png", "image_url"), | |
| ".mp4": ("video/mp4", "video_url"), | |
| ".wav": ("audio/wav", "audio_url"), | |
| }[path.suffix] | |
| encoded = base64.b64encode(path.read_bytes()).decode() | |
| media.append({"type": kind, kind: {"url": f"data:{mime};base64,{encoded}"}}) | |
| return { | |
| "model": "Premonition-Exp", | |
| "state": case["state"], | |
| "questions": case["questions"], | |
| "media": media, | |
| "samples": 1, | |
| "seed": 42, | |
| } | |
| def main(): | |
| parser = argparse.ArgumentParser(description=__doc__) | |
| parser.add_argument("--url", default="http://127.0.0.1:8011") | |
| parser.add_argument("--case", default="omni-review") | |
| parser.add_argument("--all", action="store_true") | |
| parser.add_argument("--root", type=Path, default=Path(__file__).resolve().parents[1]) | |
| args = parser.parse_args() | |
| rows = json.loads((args.root / "demo/cases.json").read_text()) | |
| selected = rows if args.all else [c for c in rows if c["id"] == args.case] | |
| if not selected: | |
| parser.error("Unknown case. Choose from: " + ", ".join(c["id"] for c in rows)) | |
| with httpx.Client(timeout=300) as client: | |
| for case in selected: | |
| response = client.post( | |
| args.url.rstrip("/") + "/v1/systemone", json=request(case, args.root) | |
| ) | |
| response.raise_for_status() | |
| print( | |
| json.dumps({"case": case["id"], "response": response.json()}, indent=2), flush=True | |
| ) | |
| if __name__ == "__main__": | |
| main() | |