Instructions to use nazimasker/Image-Caption-University-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nazimasker/Image-Caption-University-model with Transformers:

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

pipe = pipeline("image-text-to-text", model="nazimasker/Image-Caption-University-model")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("nazimasker/Image-Caption-University-model")
model = AutoModelForMultimodalLM.from_pretrained("nazimasker/Image-Caption-University-model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nazimasker/Image-Caption-University-model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/nazimasker/Image-Caption-University-model

SGLang

How to use nazimasker/Image-Caption-University-model 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 "nazimasker/Image-Caption-University-model" \
    --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": "nazimasker/Image-Caption-University-model",
		"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 "nazimasker/Image-Caption-University-model" \
        --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": "nazimasker/Image-Caption-University-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nazimasker/Image-Caption-University-model with Docker Model Runner:
```
docker model run hf.co/nazimasker/Image-Caption-University-model
```

nazimasker commited on Oct 28, 2024

Commit

b8eaee8

verified ·

1 Parent(s): c006bd5

Training in progress, step 200

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Oct28_05-15-32_195bbbbcc587/events.out.tfevents.1730092546.195bbbbcc587.806.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:448b0e10106ae883fabfb7beda82e9cfbfa4f84f0fa338203514270a61918b55
 size 706516040

 version https://git-lfs.github.com/spec/v1
+oid sha256:943d61d47d1dfe844de9104ae507ff67f6d83ea0962b8fa1a18d6c40572f99b7
 size 706516040

runs/Oct28_05-15-32_195bbbbcc587/events.out.tfevents.1730092546.195bbbbcc587.806.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc068d4d29b21423a5c3fb5a0ccaea3380f2077f9d30f48cc5de3e6a534c4616
-size 6836

 version https://git-lfs.github.com/spec/v1
+oid sha256:0d6cd42b059fdb5aad50af31791d745bc554ebf93135aaa1a61baf1cc153e3d3
+size 7371