Instructions to use suryatmodulus/GPC-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use suryatmodulus/GPC-1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="suryatmodulus/GPC-1")

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

processor = AutoProcessor.from_pretrained("suryatmodulus/GPC-1")
model = AutoModelForMultimodalLM.from_pretrained("suryatmodulus/GPC-1", device_map="auto")

PEFT
How to use suryatmodulus/GPC-1 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use suryatmodulus/GPC-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "suryatmodulus/GPC-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "suryatmodulus/GPC-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/suryatmodulus/GPC-1

SGLang

How to use suryatmodulus/GPC-1 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 "suryatmodulus/GPC-1" \
    --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": "suryatmodulus/GPC-1",
		"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 "suryatmodulus/GPC-1" \
        --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": "suryatmodulus/GPC-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use suryatmodulus/GPC-1 with Docker Model Runner:
```
docker model run hf.co/suryatmodulus/GPC-1
```

GPC-1 / demo /README.md

suryatmodulus

harshatheg

Duplicate from harshatheg/GPC-1

96a4100 17 days ago

preview code

Raw History Blame Contribute Delete

2.26 kB

metadata

title: GPC-1
emoji: ◈
colorFrom: gray
colorTo: green
sdk: gradio
sdk_version: 6.9.0
python_version: '3.12'
app_file: app.py
models:
  - harshatheg/GPC-1
short_description: Context in. Structured predictions out.
license: apache-2.0
header: mini

GPC-1 demo

Upload context, define your output, and select Run. Presets cover classification, numerical analysis, boxes, pose, pixel art, and structured decisions.

Hosted demo: ZeroGPU

The hosted demo loads GPC-1 directly on Hugging Face ZeroGPU. No separate inference server is needed. To host that version yourself, duplicate the Space, select ZeroGPU hardware, and add an HF_TOKEN secret with read access if the model requires it.

Server-backed demo

This directory contains a lightweight UI for an existing GPC-1 NVIDIA server. Start the server using the setup guide, then run these commands from the release directory:

cd demo
python -m pip install -r requirements.txt
export GPC1_API_URL=http://127.0.0.1:8000
export GPC1_API_KEY=YOUR_SERVER_KEY
python app.py

Host the server-backed UI on Spaces

Copy this directory to a Gradio Space. Configure GPC1_API_URL as the HTTPS origin of your NVIDIA server and GPC1_API_KEY as a Space secret. The lightweight UI calls the server; it does not load model weights on the Space CPU.

The key stays server-side. Requests are not retried automatically. Uploaded context is sent only to the configured model endpoint; temporary uploads are periodically removed. Images are accepted for numeric outputs. Numeric fields use finite-resolution ranges; JSON records select from the records supplied.

Input limits

The UI accepts up to 256 KiB of context text and a 4 MiB request body. The hosted ZeroGPU version also limits compiled inputs to 8,192 tokens. Use the server API directly for larger inputs; see context configuration for its 262,144-token ceiling and hardware requirements.

Model and API

The person photo used by the bounding-box and pose presets is “Tim running” by Liber4l, public domain.