Instructions to use Duyen1rt/git-base-caption with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Duyen1rt/git-base-caption with Transformers:

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

pipe = pipeline("image-text-to-text", model="Duyen1rt/git-base-caption")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Duyen1rt/git-base-caption")
model = AutoModelForImageTextToText.from_pretrained("Duyen1rt/git-base-caption")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Duyen1rt/git-base-caption with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Duyen1rt/git-base-caption"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Duyen1rt/git-base-caption",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Duyen1rt/git-base-caption

SGLang

How to use Duyen1rt/git-base-caption 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 "Duyen1rt/git-base-caption" \
    --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": "Duyen1rt/git-base-caption",
		"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 "Duyen1rt/git-base-caption" \
        --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": "Duyen1rt/git-base-caption",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Duyen1rt/git-base-caption with Docker Model Runner:
```
docker model run hf.co/Duyen1rt/git-base-caption
```

Duyen1rt commited on Feb 12, 2025

Commit

2ff4c2a

verified ·

1 Parent(s): c456927

Training in progress, step 10

Browse files

Files changed (3) hide show

model.safetensors +1 -1
runs/Feb12_04-36-53_be1b2b4cf1eb/events.out.tfevents.1739335024.be1b2b4cf1eb.1659.2 +3 -0
training_args.bin +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d94dda1b900d6158c1bc41efb41f03bf901b7117c60a5e50c41fc633edaba8fd
 size 706516040

 version https://git-lfs.github.com/spec/v1
+oid sha256:9c2bdba4bfefcbf090c184c1c55c3a57a3eba71688317bfddd041f8e45e1e1fc
 size 706516040

runs/Feb12_04-36-53_be1b2b4cf1eb/events.out.tfevents.1739335024.be1b2b4cf1eb.1659.2 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:31f44d669de28f126139b130bc55f4ce33c0c00b7ab0f8216eb7a1ef2776cab4
+size 5848

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:911b4e62bf7f21d24b26dcadab4e6d9294e92e6e3f8a24a5e0dbf6b1d7624bd3
 size 5368

 version https://git-lfs.github.com/spec/v1
+oid sha256:4358aa49d0d1d52aaa3b081455155e9d763dfa66d76fa01d2264b16f460a5f38
 size 5368