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

Libraries

How to use minwook/git-base-cartoon with Transformers:

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

pipe = pipeline("image-text-to-text", model="minwook/git-base-cartoon")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("minwook/git-base-cartoon")
model = AutoModelForImageTextToText.from_pretrained("minwook/git-base-cartoon")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use minwook/git-base-cartoon with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/minwook/git-base-cartoon

SGLang

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

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

minwook commited on Jul 31, 2024

Commit

17e74e4

verified ·

1 Parent(s): 2f006b5

Training in progress, step 280

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Jul31_05-42-20_80282c379916/events.out.tfevents.1722404686.80282c379916.4172.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff4fc306c506667145989b7ed00e5f0fdf46899134b4ebf16faedd9b7d60277
 size 706516040

 version https://git-lfs.github.com/spec/v1
+oid sha256:2088498dfbc7e969e6fe656db06746b1c5884637f38c865f2a9edc43e73137a0
 size 706516040

runs/Jul31_05-42-20_80282c379916/events.out.tfevents.1722404686.80282c379916.4172.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:561f9adb5e2cac3a019a7552477c2c188340d167ce0063b04c03c2b974cd3b6b
-size 7181

 version https://git-lfs.github.com/spec/v1
+oid sha256:964886c737b17ca9dc5a6ea4779c4e07bc6273ea32aab3880bd8b0637df7d7ed
+size 8071