Instructions to use omunaman/Open_Source_GPT_OSS_20B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use omunaman/Open_Source_GPT_OSS_20B with Transformers:

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

pipe = pipeline("text-generation", model="omunaman/Open_Source_GPT_OSS_20B")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("omunaman/Open_Source_GPT_OSS_20B", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use omunaman/Open_Source_GPT_OSS_20B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "omunaman/Open_Source_GPT_OSS_20B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "omunaman/Open_Source_GPT_OSS_20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/omunaman/Open_Source_GPT_OSS_20B

SGLang

How to use omunaman/Open_Source_GPT_OSS_20B 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 "omunaman/Open_Source_GPT_OSS_20B" \
    --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": "omunaman/Open_Source_GPT_OSS_20B",
		"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 "omunaman/Open_Source_GPT_OSS_20B" \
        --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": "omunaman/Open_Source_GPT_OSS_20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use omunaman/Open_Source_GPT_OSS_20B with Docker Model Runner:
```
docker model run hf.co/omunaman/Open_Source_GPT_OSS_20B
```

omunaman commited on Sep 3, 2025

Commit

6d06b15

verified ·

1 Parent(s): dc2f465

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -125,8 +125,8 @@ The code in the repository and the weights of this model are released under the
 If you use our codebase or find this work helpful in your research, please consider citing our repository:
 ```bibtex
-@software{Naman_GPT-OSS_Replication_2024,
-  author = {Naman, Dr. Raj Dandekar,
   title = {{An Open-Source Implementation of gpt-oss-20b}},
   month = {September},
   year = {2025},

 If you use our codebase or find this work helpful in your research, please consider citing our repository:
 ```bibtex
+@software{Vizuara_GPT-OSS_Replication_2025,
+  author = {Naman and Dr. Raj Dandekar,
   title = {{An Open-Source Implementation of gpt-oss-20b}},
   month = {September},
   year = {2025},