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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Dayhoff-170m-GR"
# 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-GR",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

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

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

sarahalamdari commited on Jul 15, 2025

Commit

c3ec161

verified ·

1 Parent(s): bbc8086

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -4,7 +4,7 @@
 # Model Card for Dayhoff
-Dayhoff is an Atlas of both protein sequence data and generative language models — a centralized resource that brings together 3.3 billion protein sequences across 1.7 billion clusters of metagenomic and natural protein sequences (GigaRef), 46 million structure-derived synthetic sequences (BackboneRef), and 16 million multiple sequence alignments (OpenProteinSet). These models can natively predict zero-shot mutation effects on fitness, scaffold structural motifs by conditioning on evolutionary or structural context, and perform guided generation of novel proteins within specified families. Learning from metagenomic and structure-based synthetic data from the Dayhoff Atlas increased the cellular expression rates of generated proteins, highlighting the real-world value of expanding the scale, diversity, and novelty of protein sequence data.
 The Dayhoff architecture is a hybrid of state-space Mamba layers and Transformer self-attention, interleaved with Mixture-of-Experts modules to maximize capacity while preserving efficiency. It natively handles long contexts, allowing both single sequences and unrolled MSAs to be modeled. Trained with an autoregressive objective in both N→C and C→N directions, Dayhoff supports order-agnostic infilling and scales to billions of parameters.

 # Model Card for Dayhoff
+Dayhoff is an Atlas of both protein sequence data and generative language models — a centralized resource that brings together 3.34 billion protein sequences across 1.7 billion clusters of metagenomic and natural protein sequences (GigaRef), 46 million structure-derived synthetic sequences (BackboneRef), and 16 million multiple sequence alignments (OpenProteinSet). These models can natively predict zero-shot mutation effects on fitness, scaffold structural motifs by conditioning on evolutionary or structural context, and perform guided generation of novel proteins within specified families. Learning from metagenomic and structure-based synthetic data from the Dayhoff Atlas increased the cellular expression rates of generated proteins, highlighting the real-world value of expanding the scale, diversity, and novelty of protein sequence data.
 The Dayhoff architecture is a hybrid of state-space Mamba layers and Transformer self-attention, interleaved with Mixture-of-Experts modules to maximize capacity while preserving efficiency. It natively handles long contexts, allowing both single sequences and unrolled MSAs to be modeled. Trained with an autoregressive objective in both N→C and C→N directions, Dayhoff supports order-agnostic infilling and scales to billions of parameters.