Instructions to use Motif-Technologies/Motif-3-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Motif-Technologies/Motif-3-Base with Transformers:

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

pipe = pipeline("text-generation", model="Motif-Technologies/Motif-3-Base", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Motif-Technologies/Motif-3-Base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Motif-Technologies/Motif-3-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Motif-Technologies/Motif-3-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Motif-Technologies/Motif-3-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Motif-Technologies/Motif-3-Base

SGLang

How to use Motif-Technologies/Motif-3-Base 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 "Motif-Technologies/Motif-3-Base" \
    --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": "Motif-Technologies/Motif-3-Base",
		"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 "Motif-Technologies/Motif-3-Base" \
        --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": "Motif-Technologies/Motif-3-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Motif-Technologies/Motif-3-Base with Docker Model Runner:
```
docker model run hf.co/Motif-Technologies/Motif-3-Base
```

leejunhyeok commited on 15 days ago

Commit

a112f98

verified ·

1 Parent(s): 2ab4351

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -101,7 +101,7 @@ We report the absolute performance of the pretrained base checkpoint under the p
 ## 5. Architecture
-Motif 3 is a fully in-house design and introduces several custom components (full details in the technical report, to be updated):
 - **Grouped Differential Latent Attention (GDLA)** — integrates grouped differential attention (asymmetric signal/noise heads with a token-dependent differential coefficient) with the compressed KV latent of Multi-head Latent Attention, plus a query-dependent output gate. Retains the expressive attention dynamics of differential attention while substantially reducing KV-cache requirements.
 - **Expert-Specific PolyNorm** — replaces the SiLU gate with a learned polynomial normalization whose coefficients are learned independently per expert, reducing activation outliers while allowing each expert to specialize.

 ## 5. Architecture
+Motif 3 is a fully in-house design and introduces several custom components (full details in the technical report):
 - **Grouped Differential Latent Attention (GDLA)** — integrates grouped differential attention (asymmetric signal/noise heads with a token-dependent differential coefficient) with the compressed KV latent of Multi-head Latent Attention, plus a query-dependent output gate. Retains the expressive attention dynamics of differential attention while substantially reducing KV-cache requirements.
 - **Expert-Specific PolyNorm** — replaces the SiLU gate with a learned polynomial normalization whose coefficients are learned independently per expert, reducing activation outliers while allowing each expert to specialize.