Instructions to use Phuree/git-base-coco-scamper4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Phuree/git-base-coco-scamper4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Phuree/git-base-coco-scamper4")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Phuree/git-base-coco-scamper4")
model = AutoModelForImageTextToText.from_pretrained("Phuree/git-base-coco-scamper4")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Phuree/git-base-coco-scamper4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Phuree/git-base-coco-scamper4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Phuree/git-base-coco-scamper4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Phuree/git-base-coco-scamper4

SGLang

How to use Phuree/git-base-coco-scamper4 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 "Phuree/git-base-coco-scamper4" \
    --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": "Phuree/git-base-coco-scamper4",
		"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 "Phuree/git-base-coco-scamper4" \
        --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": "Phuree/git-base-coco-scamper4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Phuree/git-base-coco-scamper4 with Docker Model Runner:
```
docker model run hf.co/Phuree/git-base-coco-scamper4
```

Phuree commited on Apr 23, 2024

Commit

f07d78b

verified ·

1 Parent(s): 5bc37a8

Training in progress, step 1190

Browse files

Files changed (2) hide show

model.safetensors +1 -1
training_args.bin +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:659dc500f9405b36e7b13faf4106c6752d26a1086b3d62f309cbd7a99ba7c880
 size 706516040

 version https://git-lfs.github.com/spec/v1
+oid sha256:e58fd94559b62adc0dcbed246cc6f2469ec3397e0e22423e3cd32cf6123fdedc
 size 706516040

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5373debf6d17b828a8b92aaf3bc3a5995b36aec82942029387dc7c3947f8a76
 size 4984

 version https://git-lfs.github.com/spec/v1
+oid sha256:91c09218f3fb5bc65f556a65de2d732ebcdedb9ef013856f293d91f97ad8b644
 size 4984