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
| set -euo pipefail | |
| failures=0 | |
| check_command() { | |
| local name="$1" | |
| if command -v "$name" >/dev/null 2>&1; then | |
| echo "OK command: $name -> $(command -v "$name")" | |
| else | |
| echo "FAIL command: $name" | |
| failures=$((failures + 1)) | |
| fi | |
| } | |
| check_file() { | |
| local path="$1" | |
| if [[ -f "$path" ]]; then | |
| echo "OK file: $path" | |
| else | |
| echo "FAIL file: $path" | |
| failures=$((failures + 1)) | |
| fi | |
| } | |
| echo "===== COMMANDS =====" | |
| check_command python | |
| check_command vllm | |
| check_command gcc | |
| check_command g++ | |
| check_command ninja | |
| check_command nvidia-smi | |
| echo | |
| echo "===== SYSTEM FILES =====" | |
| check_file /usr/include/python3.12/Python.h | |
| check_file /usr/lib/wsl/lib/libcuda.so | |
| echo | |
| echo "===== PYTHON PACKAGES =====" | |
| python - <<'PY' | |
| import importlib.metadata | |
| for package in ("vllm", "torch", "transformers", "compressed-tensors", "nvidia-cuda-nvrtc"): | |
| try: | |
| print(f"OK {package}: {importlib.metadata.version(package)}") | |
| except importlib.metadata.PackageNotFoundError: | |
| print(f"MISS {package}") | |
| PY | |
| echo | |
| echo "===== NVRTC FILES =====" | |
| python - <<'PY' | |
| import site | |
| from pathlib import Path | |
| found = [] | |
| for site_dir in site.getsitepackages(): | |
| for path in (Path(site_dir) / "nvidia").glob("cu*/lib/libnvrtc*.so*"): | |
| found.append(path) | |
| for path in sorted(found): | |
| print(path) | |
| if not found: | |
| raise SystemExit("No NVRTC libraries found") | |
| PY | |
| echo | |
| echo "===== CUDA DRIVER LINK =====" | |
| cat >/tmp/internvl_cuda_link_test.cpp <<'CPP' | |
| extern "C" int cuInit(unsigned int flags); | |
| int main() { return 0; } | |
| CPP | |
| LIBRARY_PATH="/usr/lib/wsl/lib:${LIBRARY_PATH:-}" \ | |
| g++ /tmp/internvl_cuda_link_test.cpp -Wl,--no-as-needed -lcuda \ | |
| -o /tmp/internvl_cuda_link_test | |
| echo "OK CUDA driver link" | |
| if [[ "$failures" -ne 0 ]]; then | |
| echo "Runtime check failed: $failures required item(s) missing." >&2 | |
| exit 1 | |
| fi | |
| echo | |
| echo "WSL RUNTIME CHECK: SUCCESS" | |