Instructions to use microsoft/Dayhoff-3b-GR-HM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Dayhoff-3b-GR-HM with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/Dayhoff-3b-GR-HM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/Dayhoff-3b-GR-HM")
model = AutoModelForCausalLM.from_pretrained("microsoft/Dayhoff-3b-GR-HM")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/Dayhoff-3b-GR-HM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Dayhoff-3b-GR-HM"
# 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-3b-GR-HM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/microsoft/Dayhoff-3b-GR-HM

SGLang

How to use microsoft/Dayhoff-3b-GR-HM 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-3b-GR-HM" \
    --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-3b-GR-HM",
		"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-3b-GR-HM" \
        --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-3b-GR-HM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use microsoft/Dayhoff-3b-GR-HM with Docker Model Runner:
```
docker model run hf.co/microsoft/Dayhoff-3b-GR-HM
```

sarahalamdari commited on Jan 26

Commit

81ffa52

verified ·

1 Parent(s): a70e0e4

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +0 -10

README.md CHANGED Viewed

@@ -8,16 +8,6 @@ tags:
 datasets:
 - microsoft/Dayhoff
 ---
----
-license: mit
-pipeline_tag: text-generation
-library_name: transformers
-tags:
-- protein-generation
-- jamba
-datasets:
-- microsoft/Dayhoff
----
 # Model Card for Dayhoff

 datasets:
 - microsoft/Dayhoff
 ---
 # Model Card for Dayhoff