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")

# 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 / docs /ARCHITECTURE.md

suryatmodulus

harshatheg

Duplicate from harshatheg/GPC-1

96a4100 2 days ago

preview code

Raw

History Blame Contribute Delete

2.11 kB

Architecture

GPC-1 uses the Qwen3.5-35B-A3B multimodal mixture-of-experts architecture with schema-bound inference. You define the output space; the server scores it and returns typed values.

Model package

model/ contains GPC-1's modified backbone weights; adapter/ contains the matching adapter applied at load time. Use both components from the same release. Qwen identifies the upstream architecture; the packaged weights belong to GPC-1.

The server loads the backbone in BF16 and the adapter in FP32. It uses the existing language-model output projection to score the request's allowed outputs.

Mode	Output
Categorical	A selected label and probabilities over your choices
Numeric	A grid estimate, probability-weighted mean, and distribution per field
Image numeric	Numeric fields conditioned on one image
Finite joint	A selected complete record and probabilities over allowed records

Numeric ranges

For bounds [minimum, maximum], the 101-point grid is:

value(i) = minimum + (maximum - minimum) × i / 100

Numeric fields share one model pass. Each returns a marginal distribution; shared context does not make them a full joint distribution. The probability-weighted mean can fall between grid positions. Angles and other circular quantities need application-specific interpretation.

Dependent records

Finite-joint mode scores complete records rather than choosing their fields independently. Probabilities are conditional on the supplied records. Compute and memory grow with the number and length of candidates.

Serving

The runtime verifies packaged asset identities, uses request-local execution, and rejects over-limit inputs without truncation. Its input ceiling is 256K tokens (262,144), including compiled request overhead. See context configuration for deployment requirements. Preserve the supplied precision, prompt formatting, and token mapping when reproducing outputs. Scale concurrent traffic with separate replicas.

See the API guide for request formats and limits.