Instructions to use WhirlwindAI/Arithmetic-SLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WhirlwindAI/Arithmetic-SLM with Transformers:

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

pipe = pipeline("text-generation", model="WhirlwindAI/Arithmetic-SLM", trust_remote_code=True, device_map="auto")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("WhirlwindAI/Arithmetic-SLM", trust_remote_code=True, dtype="auto", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WhirlwindAI/Arithmetic-SLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/WhirlwindAI/Arithmetic-SLM

SGLang

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

Docker Model Runner
How to use WhirlwindAI/Arithmetic-SLM with Docker Model Runner:
```
docker model run hf.co/WhirlwindAI/Arithmetic-SLM
```

PhysiQuanty commited on 14 days ago

Commit

01ed511

verified ·

1 Parent(s): a952cc2

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -274,7 +274,7 @@ Expected style:
 We will continue improving our dataset engineering, but more importantly, we want to teach the model what most models are never explicitly taught:
 - **Binary calculation:** Neural Application Binary Interface, or **NABI**, with 16-bit numerical structures, including floats.
-- **FP16 to base-65k conversion:** a `float16` value is represented by 2 bytes, meaning 65,536 possible bit patterns. Base 65,536 also contains 65,536 possible integer values, making exact bit-level mapping possible.
 - **Dot-product learning:** explicit learning of scalar products on `float16` vectors with 16, 8, 4, and 2 dimensions.
 - **Learning the dynamics of its own learning:** training the model to predict its own weights and gradients over time, including its own gradient descent dynamics.

 We will continue improving our dataset engineering, but more importantly, we want to teach the model what most models are never explicitly taught:
 - **Binary calculation:** Neural Application Binary Interface, or **NABI**, with 16-bit numerical structures, including floats.
+- **FP16 to BASE-65,536 conversion:** a `float16` value is represented by 2 bytes, meaning 65,536 possible bit patterns. Base 65,536 also contains 65,536 possible integer values, making exact bit-level mapping possible.
 - **Dot-product learning:** explicit learning of scalar products on `float16` vectors with 16, 8, 4, and 2 dimensions.
 - **Learning the dynamics of its own learning:** training the model to predict its own weights and gradients over time, including its own gradient descent dynamics.