Instructions to use linhtrann21/ft_paligemma_ocr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use linhtrann21/ft_paligemma_ocr with Transformers:

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

pipe = pipeline("image-text-to-text", model="linhtrann21/ft_paligemma_ocr")

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

processor = AutoProcessor.from_pretrained("linhtrann21/ft_paligemma_ocr")
model = AutoModelForMultimodalLM.from_pretrained("linhtrann21/ft_paligemma_ocr", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use linhtrann21/ft_paligemma_ocr with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "linhtrann21/ft_paligemma_ocr"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "linhtrann21/ft_paligemma_ocr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/linhtrann21/ft_paligemma_ocr

SGLang

How to use linhtrann21/ft_paligemma_ocr 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 "linhtrann21/ft_paligemma_ocr" \
    --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": "linhtrann21/ft_paligemma_ocr",
		"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 "linhtrann21/ft_paligemma_ocr" \
        --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": "linhtrann21/ft_paligemma_ocr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use linhtrann21/ft_paligemma_ocr with Docker Model Runner:
```
docker model run hf.co/linhtrann21/ft_paligemma_ocr
```

linhtrann21 commited on Dec 10, 2024

Commit

ef67544

verified ·

1 Parent(s): 67c5ae0

Training in progress, step 8000

Browse files

Files changed (3) hide show

model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1
runs/Dec10_02-42-02_9a6afece985e/events.out.tfevents.1733798702.9a6afece985e.6735.1 +2 -2

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1872bea97ef3103378e823b2459a27a14a44567fc213d814e59f8a6be7f99f8
 size 4985044392

 version https://git-lfs.github.com/spec/v1
+oid sha256:09cf2d659c6a5c3926a6b209616dadd6958033eaaa819ed7fb932d8b201ae7bc
 size 4985044392

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:419e3d5a81afa27ea7e3718abd4415ac1ceb017917522990c1153a7e9aa37ff8
 size 861970608

 version https://git-lfs.github.com/spec/v1
+oid sha256:020eaf4d20d1eb62fac341727e805066df4c6b6aba675ebcc43ae23fd64eccc4
 size 861970608

runs/Dec10_02-42-02_9a6afece985e/events.out.tfevents.1733798702.9a6afece985e.6735.1 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d38a87b69b18300525f4906fcc7d436c0eba10061c6e0f5b8e0df6f1bfefdaa5
-size 20115

 version https://git-lfs.github.com/spec/v1
+oid sha256:fcddfc9be5ee832f209c6f5076cec63466f5098ad9e5406b37534bd7d582ed68
+size 22225