Instructions to use ml-ryanlee/looped-16x2-d640-1e18 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ml-ryanlee/looped-16x2-d640-1e18 with Transformers:

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

pipe = pipeline("text-generation", model="ml-ryanlee/looped-16x2-d640-1e18", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ml-ryanlee/looped-16x2-d640-1e18", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ml-ryanlee/looped-16x2-d640-1e18 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ml-ryanlee/looped-16x2-d640-1e18"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ml-ryanlee/looped-16x2-d640-1e18",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ml-ryanlee/looped-16x2-d640-1e18

SGLang

How to use ml-ryanlee/looped-16x2-d640-1e18 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 "ml-ryanlee/looped-16x2-d640-1e18" \
    --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": "ml-ryanlee/looped-16x2-d640-1e18",
		"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 "ml-ryanlee/looped-16x2-d640-1e18" \
        --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": "ml-ryanlee/looped-16x2-d640-1e18",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ml-ryanlee/looped-16x2-d640-1e18 with Docker Model Runner:
```
docker model run hf.co/ml-ryanlee/looped-16x2-d640-1e18
```

looped-32L-d640-1e18

32-layer compute-optimal checkpoint for Sparse Layers are Critical to Scaling Looped Language Models (arXiv:2605.09165).


architecture	`looped`
d_model	640
effective layers	32
compute budget	1e18 FLOPs
training steps	45,632
parameters (stored)	143,627,520
peak LR	0.005
batch size	16
muP width_ratio	2.5 (d_base=256)
final val loss	n/a

This width is the architecture's measured minimum on a ten-rung isoFLOP sweep (d256-d1408) at 1e18 FLOPs.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained(
    "ml-ryanlee/looped-32L-d640-1e18", trust_remote_code=True)
tok = AutoTokenizer.from_pretrained("gpt2")

Pass max_length=1024 when evaluating — the RoPE buffer is sized to the training context.

Downloads last month: 23

Safetensors

Model size

0.1B params

Tensor type

F32

Paper for ml-ryanlee/looped-16x2-d640-1e18

Sparse Layers are Critical to Scaling Looped Language Models

Paper • 2605.09165 • Published May 9