Instructions to use Jwalit/gemma4-e4b-kyc-document-extractor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jwalit/gemma4-e4b-kyc-document-extractor with Transformers:

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

pipe = pipeline("image-text-to-text", model="Jwalit/gemma4-e4b-kyc-document-extractor")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Jwalit/gemma4-e4b-kyc-document-extractor", dtype="auto")

PEFT
How to use Jwalit/gemma4-e4b-kyc-document-extractor with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jwalit/gemma4-e4b-kyc-document-extractor with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jwalit/gemma4-e4b-kyc-document-extractor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jwalit/gemma4-e4b-kyc-document-extractor",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Jwalit/gemma4-e4b-kyc-document-extractor

SGLang

How to use Jwalit/gemma4-e4b-kyc-document-extractor 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 "Jwalit/gemma4-e4b-kyc-document-extractor" \
    --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": "Jwalit/gemma4-e4b-kyc-document-extractor",
		"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 "Jwalit/gemma4-e4b-kyc-document-extractor" \
        --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": "Jwalit/gemma4-e4b-kyc-document-extractor",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Jwalit/gemma4-e4b-kyc-document-extractor with Docker Model Runner:
```
docker model run hf.co/Jwalit/gemma4-e4b-kyc-document-extractor
```

Jwalit commited on Apr 23

Commit

bf014b7

verified ·

1 Parent(s): 15dad3d

Add dataset generation script reference

Browse files

Files changed (1) hide show

generate_kyc_dataset.py +20 -0

generate_kyc_dataset.py ADDED Viewed

	@@ -0,0 +1,20 @@

+"""
+Generate a synthetic KYC document dataset for training a VLM on document
+extraction and classification tasks.
+Produces document images for: Aadhar, PAN, Passport, Visa, Election Card
+with corresponding extraction ground truth in JSON format.
+Usage:
+    pip install datasets Pillow faker huggingface_hub
+    python generate_kyc_dataset.py
+Output: Pushes to HuggingFace Hub as Jwalit/kyc-document-extraction-vlm
+"""
+# See full script at: https://huggingface.co/datasets/Jwalit/kyc-document-extraction-vlm
+# The dataset has already been generated and pushed.
+# Re-run this script only if you want to regenerate with different parameters.
+print("Dataset already generated at: https://huggingface.co/datasets/Jwalit/kyc-document-extraction-vlm")
+print("To regenerate, uncomment the code below and run.")