Instructions to use percepta-ai/spotlight-vm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use percepta-ai/spotlight-vm with Transformers:

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

pipe = pipeline("text-generation", model="percepta-ai/spotlight-vm", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("percepta-ai/spotlight-vm", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use percepta-ai/spotlight-vm with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/percepta-ai/spotlight-vm

SGLang

How to use percepta-ai/spotlight-vm 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 "percepta-ai/spotlight-vm" \
    --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": "percepta-ai/spotlight-vm",
		"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 "percepta-ai/spotlight-vm" \
        --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": "percepta-ai/spotlight-vm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use percepta-ai/spotlight-vm with Docker Model Runner:
```
docker model run hf.co/percepta-ai/spotlight-vm
```

spotlight-vm / README.md

zhenggq

Update README.md

00acba5 verified 9 days ago

preview code

Raw History Blame Contribute Delete

1.75 kB

	---
	license: apache-2.0
	library_name: transformers
	---

	# Spotlight VM

	A small, hand-constructed [Spotlight](https://percepta.ai/blog/spotlight-memory) transformer that runs Python:
	the examples from [Can LLMs Grow Their Own Capabilities?](https://percepta.ai/blog/can-llms-grow-their-own-capabilities).
	`intelligence/` holds the weights (under 100K parameters), which never change. `memory/` holds MicroPython
	v1.28.0 (`core.safetensors`) and two packages.

	```sh
	cc -O3 -std=c99 spotlight.c -lm -o spotlight
	./spotlight < examples/euler1.py # 233168; -v also prints every generated token
	cat examples/tax_brackets/*.py \| ./spotlight
	```

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model = AutoModelForCausalLM.from_pretrained("percepta-ai/spotlight-vm", trust_remote_code=True)
	tokenizer = AutoTokenizer.from_pretrained("percepta-ai/spotlight-vm", trust_remote_code=True)
	output = model.generate(**tokenizer("print(1 + 2)\n", return_tensors="pt"))
	print(tokenizer.decode(output[0])) # 3
	```

	In a local copy of this folder, `from_pretrained(".")` works the same way.

	\| Example \| In the post \| Output \|
	\|---\|---\|---\|
	\| `examples/euler1.py`, `euler2.py`, `euler3.py` \| Project Euler problems 1 to 3 \| `233168`, `4613732`, `6857` \|
	\| `examples/memory_loader.py` \| Loading memory selectively \| `4` \|
	\| `examples/tax_brackets/` \| Acquiring and updating knowledge \| `$17400`, then `$16914` \|
	\| `examples/mnist_digit.py` \| Growing capabilities and intelligence \| `7` \|

	It runs on one CPU core at about 120K tokens per second: minutes for the Project Euler examples,
	about half an hour for MNIST (245M tokens). This MicroPython build has no floating point. License: Apache 2.0,
	see [LICENSE.md](LICENSE.md).