Instructions to use MS-ML/SpecTUS_pretrained_only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MS-ML/SpecTUS_pretrained_only with Transformers:

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

pipe = pipeline("text-generation", model="MS-ML/SpecTUS_pretrained_only")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("MS-ML/SpecTUS_pretrained_only")
model = AutoModelForSeq2SeqLM.from_pretrained("MS-ML/SpecTUS_pretrained_only", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MS-ML/SpecTUS_pretrained_only with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MS-ML/SpecTUS_pretrained_only

SGLang

How to use MS-ML/SpecTUS_pretrained_only 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 "MS-ML/SpecTUS_pretrained_only" \
    --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": "MS-ML/SpecTUS_pretrained_only",
		"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 "MS-ML/SpecTUS_pretrained_only" \
        --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": "MS-ML/SpecTUS_pretrained_only",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MS-ML/SpecTUS_pretrained_only with Docker Model Runner:
```
docker model run hf.co/MS-ML/SpecTUS_pretrained_only
```

SpecTUS_pretrained_only

Commit History

Sep 3

06:04
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
cfeb719

Aug 12

14:07
cc by-nc

krenek

Verified signature
1218bd9

Jul 21

14:47
NIST license; published paper (#5)⁠

hajekad +1: krenek

bc81d8b

Sep 19, 2025

10:24
Update README.md

hajekad

Verified signature
f762708
10:19
Update README.md

hajekad

Verified signature
70c4582

Feb 6, 2025

10:56
Update config.json

hajekad

Verified signature
ef887dc
10:56
Delete MS-ML/SpecTUS_pretrained_only/config.json

hajekad

Verified signature
9436715
10:54
Upload MS-ML/SpecTUS_pretrained_only/config.json with huggingface_hub

hajekad

Verified signature
f902664
10:34
Update README.md

hajekad

Verified signature
6266e17
10:09
Upload folder using huggingface_hub (#2)⁠

hajekad

Verified signature
eabf59b

Dec 2, 2024

19:08
Update README.md

hajekad

Verified signature
8a6e0f3
19:00
Update README.md

hajekad

Verified signature
aab53be
18:58
Update README.md

hajekad

Verified signature
1de3670
18:56
Update README.md

hajekad

Verified signature
36f748e
18:55
Update README.md

hajekad

Verified signature
7d1b679
17:19
Upload folder using huggingface_hub (#1)⁠

hajekad

Verified signature
b333ffd
16:00
Update README.md

hajekad

Verified signature
fb00795
15:59
initial commit

hajekad

Verified signature
9e19f4e

Commit History

Sep 3

Adding `safetensors` variant of this model⁠

Aug 12

cc by-nc

Jul 21

NIST license; published paper (#5)⁠

Sep 19, 2025

Update README.md

Update README.md

Feb 6, 2025

Update config.json

Delete MS-ML/SpecTUS_pretrained_only/config.json

Upload MS-ML/SpecTUS_pretrained_only/config.json with huggingface_hub

Update README.md

Upload folder using huggingface_hub (#2)⁠

Dec 2, 2024

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Upload folder using huggingface_hub (#1)⁠

Update README.md

initial commit