Image-Text-to-Text
Transformers
Safetensors
English
Chinese
Korean
internvl
internvl3.5
vision-language
multimodal
vllm
compressed-tensors
fp8
w8a16
ampere
wsl2
conversational
Instructions to use hsmin92/internvl35-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hsmin92/internvl35-fp8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="hsmin92/internvl35-fp8") 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("hsmin92/internvl35-fp8") model = AutoModelForMultimodalLM.from_pretrained("hsmin92/internvl35-fp8", 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 hsmin92/internvl35-fp8 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hsmin92/internvl35-fp8" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hsmin92/internvl35-fp8", "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/hsmin92/internvl35-fp8
- SGLang
How to use hsmin92/internvl35-fp8 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 "hsmin92/internvl35-fp8" \ --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": "hsmin92/internvl35-fp8", "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 "hsmin92/internvl35-fp8" \ --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": "hsmin92/internvl35-fp8", "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 hsmin92/internvl35-fp8 with Docker Model Runner:
docker model run hf.co/hsmin92/internvl35-fp8
| #!/usr/bin/env python3 | |
| from __future__ import annotations | |
| import argparse | |
| import base64 | |
| import json | |
| import mimetypes | |
| import sys | |
| import urllib.error | |
| import urllib.request | |
| from pathlib import Path | |
| def build_data_url(image_path: Path) -> str: | |
| mime_type, _ = mimetypes.guess_type(image_path.name) | |
| if mime_type is None or not mime_type.startswith("image/"): | |
| mime_type = "image/jpeg" | |
| encoded = base64.b64encode(image_path.read_bytes()).decode("ascii") | |
| return f"data:{mime_type};base64,{encoded}" | |
| def main() -> int: | |
| parser = argparse.ArgumentParser(description="Send a local image to the vLLM OpenAI API.") | |
| parser.add_argument("image", type=Path, help="Path to a local image") | |
| parser.add_argument("prompt", nargs="?", default="Describe this image in detail.") | |
| parser.add_argument("--api-base", default="http://127.0.0.1:8000/v1") | |
| parser.add_argument("--model", default="internvl35-fp8") | |
| parser.add_argument("--max-tokens", type=int, default=256) | |
| args = parser.parse_args() | |
| if not args.image.is_file(): | |
| print(f"Image not found: {args.image}", file=sys.stderr) | |
| return 2 | |
| payload = { | |
| "model": args.model, | |
| "messages": [ | |
| { | |
| "role": "user", | |
| "content": [ | |
| {"type": "image_url", "image_url": {"url": build_data_url(args.image)}}, | |
| {"type": "text", "text": args.prompt}, | |
| ], | |
| } | |
| ], | |
| "temperature": 0.0, | |
| "max_tokens": args.max_tokens, | |
| } | |
| request = urllib.request.Request( | |
| f"{args.api_base.rstrip('/')}/chat/completions", | |
| data=json.dumps(payload).encode("utf-8"), | |
| headers={"Content-Type": "application/json"}, | |
| method="POST", | |
| ) | |
| try: | |
| with urllib.request.urlopen(request, timeout=300) as response: | |
| result = json.load(response) | |
| except urllib.error.HTTPError as exc: | |
| print(exc.read().decode("utf-8", errors="replace"), file=sys.stderr) | |
| return 1 | |
| except urllib.error.URLError as exc: | |
| print(f"Request failed: {exc}", file=sys.stderr) | |
| return 1 | |
| print(result["choices"][0]["message"]["content"]) | |
| return 0 | |
| if __name__ == "__main__": | |
| raise SystemExit(main()) | |