Instructions to use ThingAI/ARK-270M-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ThingAI/ARK-270M-Base with Transformers:

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

pipe = pipeline("text-generation", model="ThingAI/ARK-270M-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("ThingAI/ARK-270M-Base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ThingAI/ARK-270M-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ThingAI/ARK-270M-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": "ThingAI/ARK-270M-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ThingAI/ARK-270M-Base

SGLang

How to use ThingAI/ARK-270M-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 "ThingAI/ARK-270M-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": "ThingAI/ARK-270M-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 "ThingAI/ARK-270M-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": "ThingAI/ARK-270M-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ThingAI/ARK-270M-Base with Docker Model Runner:
```
docker model run hf.co/ThingAI/ARK-270M-Base
```

ThingsAI commited on Jun 6

Commit

ba368af

verified ·

1 Parent(s): 33147aa

Upload model.safetensors with huggingface_hub

Browse files

Files changed (1) hide show

model.safetensors +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c95f6f6fa19acd21f62e96b026058d5c5db0c9b6c4b40dc8c2e2bffb3defa34
-size 503537024

 version https://git-lfs.github.com/spec/v1
+oid sha256:449e6a884fad3f8008e0806e03fc83cda5c99bcf45c7ddbb7e63b2defbe92e3c
+size 604200408