Instructions to use North-ML1/Wind-Edge-1.6-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use North-ML1/Wind-Edge-1.6-Base with Transformers:

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

pipe = pipeline("text-generation", model="North-ML1/Wind-Edge-1.6-Base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("North-ML1/Wind-Edge-1.6-Base", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use North-ML1/Wind-Edge-1.6-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "North-ML1/Wind-Edge-1.6-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "North-ML1/Wind-Edge-1.6-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/North-ML1/Wind-Edge-1.6-Base

SGLang

How to use North-ML1/Wind-Edge-1.6-Base 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 "North-ML1/Wind-Edge-1.6-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "North-ML1/Wind-Edge-1.6-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "North-ML1/Wind-Edge-1.6-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "North-ML1/Wind-Edge-1.6-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use North-ML1/Wind-Edge-1.6-Base with Docker Model Runner:
```
docker model run hf.co/North-ML1/Wind-Edge-1.6-Base
```

Wind Edge 1.6 (SFT)

Compact dense decoder-only transformer for edge inference.

Architecture

Wind Edge is a custom dense transformer (RMSNorm + RoPE + GQA + SwiGLU) with per-head Q/K normalization. Includes its own WindEdgeForCausalLM / WindEdgeConfig classes — load with trust_remote_code=True.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("arthu1/wind-edge-1.6-sft", trust_remote_code=True)
tok = AutoTokenizer.from_pretrained("arthu1/wind-edge-1.6-sft")

Pipeline

Continued pretraining on GLM reasoning, CodeX thinking, and Nemotron post-training data.
Supervised fine-tuning on Wind Edge SFT, identity pairs, Claude-style assistant data, and safety/chat rows.
Depth pruning (block-influence) to ~0.45B parameters.

Downloads last month: 94

Safetensors

Model size

0.4B params

Tensor type

F32

Model tree for North-ML1/Wind-Edge-1.6-Base

Finetunes

1 model

Collection including North-ML1/Wind-Edge-1.6-Base

North ML Version 1

Collection

3 items • Updated 6 days ago