Instructions to use LongSafari/hyenadna-large-1m-seqlen-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LongSafari/hyenadna-large-1m-seqlen-hf with Transformers:

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

pipe = pipeline("text-generation", model="LongSafari/hyenadna-large-1m-seqlen-hf", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("LongSafari/hyenadna-large-1m-seqlen-hf", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LongSafari/hyenadna-large-1m-seqlen-hf with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/LongSafari/hyenadna-large-1m-seqlen-hf

SGLang

How to use LongSafari/hyenadna-large-1m-seqlen-hf 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 "LongSafari/hyenadna-large-1m-seqlen-hf" \
    --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": "LongSafari/hyenadna-large-1m-seqlen-hf",
		"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 "LongSafari/hyenadna-large-1m-seqlen-hf" \
        --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": "LongSafari/hyenadna-large-1m-seqlen-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LongSafari/hyenadna-large-1m-seqlen-hf with Docker Model Runner:
```
docker model run hf.co/LongSafari/hyenadna-large-1m-seqlen-hf
```

Attention mask

by tanhevg - opened Dec 26, 2023

Discussion

tanhevg

Dec 26, 2023

Hi there! Thank you for the great model. Any reason why the attention mask has been removed in the latest version? It's kind of inconsistent with other checkpoints ('medium' and others).

Thanks in advance,
Evgeny

Rocketknight1

LongSafari org Jan 18, 2024

Hi @tanhevg - this is my fault, I'm sorry! We actually plan to propagate this change to all of the HyenaDNA models, since the attention mask doesn't really work for Hyena in the same way that it does in transformers. I'm sorry for the period of incompatibility between 1M and the other sizes, but the others will have the new behaviour very soon!

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