Instructions to use fischju/glimpse-v1-openvino with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fischju/glimpse-v1-openvino with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="fischju/glimpse-v1-openvino")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("fischju/glimpse-v1-openvino")
model = AutoModelForMultimodalLM.from_pretrained("fischju/glimpse-v1-openvino")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fischju/glimpse-v1-openvino with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fischju/glimpse-v1-openvino"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fischju/glimpse-v1-openvino",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fischju/glimpse-v1-openvino

SGLang

How to use fischju/glimpse-v1-openvino 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 "fischju/glimpse-v1-openvino" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fischju/glimpse-v1-openvino",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "fischju/glimpse-v1-openvino" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fischju/glimpse-v1-openvino",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fischju/glimpse-v1-openvino with Docker Model Runner:
```
docker model run hf.co/fischju/glimpse-v1-openvino
```

This model was converted to OpenVINO from llmvision/glimpse-v1 using optimum-intel via the export space.

First make sure you have optimum-intel installed:

pip install optimum[openvino]

To load your model you can do as follows:

from optimum.intel import OVModelForVisualCausalLM

model_id = "fischju/glimpse-v1-openvino"
model = OVModelForVisualCausalLM.from_pretrained(model_id)

Downloads last month: 9

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for fischju/glimpse-v1-openvino

Base model

google/gemma-3-4b-pt

Quantized

llmvision/glimpse-v1

Finetuned

(1)

this model