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

Libraries

How to use lasenku/git-base-onepiece with Transformers:

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

pipe = pipeline("image-text-to-text", model="lasenku/git-base-onepiece")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("lasenku/git-base-onepiece")
model = AutoModelForMultimodalLM.from_pretrained("lasenku/git-base-onepiece")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lasenku/git-base-onepiece with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/lasenku/git-base-onepiece

SGLang

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

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

lasenku commited on Mar 28, 2024

Commit

0ab5241

verified ·

1 Parent(s): 6f071ee

Training in progress, step 150

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Mar28_14-39-02_fc569563731f/events.out.tfevents.1711636743.fc569563731f.4295.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a8d1df1b3cba5399173239a5469354954476a27bfdff1c5c9282ae368e5e086
 size 706516040

 version https://git-lfs.github.com/spec/v1
+oid sha256:ef7848aadd25f05ec6fa4cbbf3000869448e81f98ff805c86d70db65c3e3c213
 size 706516040

runs/Mar28_14-39-02_fc569563731f/events.out.tfevents.1711636743.fc569563731f.4295.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f803f8020ef1a189edcf38aa0188850afbc235590a93d9c8206c84ca5662ee7
-size 5313

 version https://git-lfs.github.com/spec/v1
+oid sha256:2836fc9ec180ac39060c16efbe8c0434e060109cc615512505b03449b58bb95c
+size 6373