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

Libraries

How to use botbottingbot/Modular_Intelligence with Transformers:

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

pipe = pipeline("text-generation", model="botbottingbot/Modular_Intelligence")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("botbottingbot/Modular_Intelligence", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use botbottingbot/Modular_Intelligence with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/botbottingbot/Modular_Intelligence

SGLang

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

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

botbottingbot commited on Nov 18, 2025

Commit

6aea657

verified ·

1 Parent(s): bb444e1

Create Readme.md

Browse files

Files changed (1) hide show

Readme.md +31 -0

Readme.md ADDED Viewed

	@@ -0,0 +1,31 @@

+# Modular Intelligence — HuggingFace Demo
+This Space demonstrates a universal, domain-agnostic **Modular Intelligence** framework:
+- Generators (modules)
+- Checkers (verification)
+- Structured outputs
+- Deterministic patterns
+- Zero vendor-lock
+## Features
+- Universal modules: analysis, explanation, strategy, writing, systems
+- Paired checker modules
+- Completely general — works for any domain
+- No backend required (runs on HF free CPU)
+- Clean architecture, extendable
+## Files
+- `modules.json` — module & checker repository
+- `app.py` — UI + orchestration
+- `requirements.txt` — dependencies
+- `diagram.txt` — architecture visualization
+## What to customize
+- Add modules
+- Add checkers
+- Swap model (e.g., Mistral 7B, Llama 3 8B, Gemma 2B)
+- Add your own structured output patterns
+## License
+MIT — you keep full IP on your architecture.