Instructions to use Snowflake/snowflake-arctic-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Snowflake/snowflake-arctic-instruct with Transformers:

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

pipe = pipeline("text-generation", model="Snowflake/snowflake-arctic-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Snowflake/snowflake-arctic-instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Snowflake/snowflake-arctic-instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Snowflake/snowflake-arctic-instruct

SGLang

How to use Snowflake/snowflake-arctic-instruct 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 "Snowflake/snowflake-arctic-instruct" \
    --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": "Snowflake/snowflake-arctic-instruct",
		"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 "Snowflake/snowflake-arctic-instruct" \
        --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": "Snowflake/snowflake-arctic-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Snowflake/snowflake-arctic-instruct with Docker Model Runner:
```
docker model run hf.co/Snowflake/snowflake-arctic-instruct
```

context length

by pateco - opened Apr 24, 2024

Discussion

pateco

Apr 24, 2024

•

edited Apr 24, 2024

What is the context length of this model, and what tokenizer does it use?

pateco

Apr 24, 2024

•

edited Apr 24, 2024

Arctic is trained using a 4K attention context window. We are developing an attention-sinks-based sliding window implementation to support unlimited sequence generation capability in the coming weeks. We look forward to working with the community to extend to a 32K attention window in the near future.

https://www.snowflake.com/blog/arctic-open-efficient-foundation-language-models-snowflake/

when counting tokens with cl100k_base I can only get to ~3k when testing in the example app, https://arctic.streamlit.app/

zheweiyao

Apr 24, 2024

•

edited Apr 24, 2024

The model is trained with 4k dense attention and the tokenizer is adopted from LLaMa-2.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment