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

Libraries

How to use lenashamseldin/git-base-prod-floors with Transformers:

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

pipe = pipeline("image-text-to-text", model="lenashamseldin/git-base-prod-floors")

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

processor = AutoProcessor.from_pretrained("lenashamseldin/git-base-prod-floors")
model = AutoModelForMultimodalLM.from_pretrained("lenashamseldin/git-base-prod-floors", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lenashamseldin/git-base-prod-floors with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/lenashamseldin/git-base-prod-floors

SGLang

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

Docker Model Runner
How to use lenashamseldin/git-base-prod-floors with Docker Model Runner:
```
docker model run hf.co/lenashamseldin/git-base-prod-floors
```

lenashamseldin commited on Jun 4, 2024

Commit

a4bd593

verified ·

1 Parent(s): 47fa4e6

Training in progress, step 650

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Jun04_17-25-07_146-235-232-42/events.out.tfevents.1717521918.146-235-232-42.2949.3 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b606e68ab3cbd3ebca30bb80d674865195c8f6c1556ee611d2eeee273d0fca5
 size 706516040

 version https://git-lfs.github.com/spec/v1
+oid sha256:0d71f058b90539297ad2fb76937e8a8200e0e7ee25f921a1cf882cb030feac15
 size 706516040

runs/Jun04_17-25-07_146-235-232-42/events.out.tfevents.1717521918.146-235-232-42.2949.3 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1b1483fa0748958ae21ba6a1581fbae34d52581d0e4d0b6d5edcb43c966ec1
-size 10910

 version https://git-lfs.github.com/spec/v1
+oid sha256:c8c59ea47e7f09774e2dd4fec36eeaad55239dc141330a70b4f62672402514a5
+size 11980