Instructions to use HuggingFaceTB/cosmo-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceTB/cosmo-1b with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceTB/cosmo-1b")

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

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/cosmo-1b")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/cosmo-1b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceTB/cosmo-1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/cosmo-1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/cosmo-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceTB/cosmo-1b

SGLang

How to use HuggingFaceTB/cosmo-1b 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 "HuggingFaceTB/cosmo-1b" \
    --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": "HuggingFaceTB/cosmo-1b",
		"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 "HuggingFaceTB/cosmo-1b" \
        --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": "HuggingFaceTB/cosmo-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceTB/cosmo-1b with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/cosmo-1b
```

cosmo-1b

Commit History

Jun 12, 2025

14:30
add AIBOM⁠

RiccardoDav

Verified signature
6e31006

Jul 8, 2024

14:47
Update config.json

anton-l HF Staff

Verified signature
e700c48

Feb 23, 2024

23:01
Update README.md

loubnabnl HF Staff

Verified signature
0d5e341
22:54
Update README.md

loubnabnl HF Staff

Verified signature
bb71039
15:26
Update README.md

loubnabnl HF Staff

Verified signature
b8c1842

Feb 20, 2024

21:16
Update README.md

loubnabnl HF Staff

Verified signature
ffb89c5
18:29
Update README.md

loubnabnl HF Staff

Verified signature
ebe19d3
18:29
Update README.md

loubnabnl HF Staff

Verified signature
a6db4d4
16:39
Update README.md

loubnabnl HF Staff

Verified signature
cafb59c
16:33
Upload 4 files

loubnabnl HF Staff

Verified signature
bb9fb35
16:02
Update README.md

loubnabnl HF Staff

Verified signature
f1d7a8f
15:54
Update README.md

loubnabnl HF Staff

Verified signature
a4c852f
15:00
Update README.md

loubnabnl HF Staff

Verified signature
68d9f23
15:00
Update README.md

loubnabnl HF Staff

Verified signature
09ec5a3

Feb 19, 2024

19:01
Create README.md

loubnabnl HF Staff

Verified signature
5aa7b2d
18:22
add model iter 140k

loubnabnl HF Staff

818b640
16:14
initial commit

loubnabnl HF Staff

Verified signature
4466e0a

Commit History

Jun 12, 2025

add AIBOM⁠

Jul 8, 2024

Update config.json

Feb 23, 2024

Update README.md

Update README.md

Update README.md

Feb 20, 2024

Update README.md

Update README.md

Update README.md

Update README.md

Upload 4 files

Update README.md

Update README.md

Update README.md

Update README.md

Feb 19, 2024

Create README.md

add model iter 140k

initial commit