Instructions to use microsoft/Dayhoff-170m-UR90 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Dayhoff-170m-UR90 with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/Dayhoff-170m-UR90")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/Dayhoff-170m-UR90")
model = AutoModelForCausalLM.from_pretrained("microsoft/Dayhoff-170m-UR90")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/Dayhoff-170m-UR90 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Dayhoff-170m-UR90"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Dayhoff-170m-UR90",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/microsoft/Dayhoff-170m-UR90

SGLang

How to use microsoft/Dayhoff-170m-UR90 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 "microsoft/Dayhoff-170m-UR90" \
    --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": "microsoft/Dayhoff-170m-UR90",
		"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 "microsoft/Dayhoff-170m-UR90" \
        --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": "microsoft/Dayhoff-170m-UR90",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use microsoft/Dayhoff-170m-UR90 with Docker Model Runner:
```
docker model run hf.co/microsoft/Dayhoff-170m-UR90
```

Update `README.md` with metadata

by alvarobartt HF Staff - opened Dec 2, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

alvarobartt

Microsoft org Dec 2, 2025

This PR updates the metadata in the README.md file to include the license (MIT inherited from https://github.com/microsoft/dayhoff), pipeline, library, and dataset; which all help with visibility, transparency and discoverability in the Hugging Face Hub.

Note that the paper would be automatically linked when the URL is included within the README.md, but at the moment only Arxiv is supported, and given that the paper has been published in bioRxiv it won't be linked yet, but still would be great to include the reference to the paper somewhere in the README.

Update `README.md` with metadata249ff666

sarahalamdari changed pull request status to merged Dec 4, 2025

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