Instructions to use Inferless/gpt-oss-20b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Inferless/gpt-oss-20b with Transformers:

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

pipe = pipeline("text-generation", model="Inferless/gpt-oss-20b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Inferless/gpt-oss-20b")
model = AutoModelForCausalLM.from_pretrained("Inferless/gpt-oss-20b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Inferless/gpt-oss-20b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Inferless/gpt-oss-20b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Inferless/gpt-oss-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Inferless/gpt-oss-20b

SGLang

How to use Inferless/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 "Inferless/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/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Inferless/gpt-oss-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Inferless/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/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Inferless/gpt-oss-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Inferless/gpt-oss-20b with Docker Model Runner:
```
docker model run hf.co/Inferless/gpt-oss-20b
```

rbgo commited on Aug 6, 2025

Commit

14713aa

verified ·

1 Parent(s): 7d21dd2

Update README.md

Browse files

Files changed (1) hide show

README.md +25 -3

README.md CHANGED Viewed

@@ -4,6 +4,7 @@ pipeline_tag: text-generation
 library_name: transformers
 tags:
 - vllm
 ---
 <p align="center">
@@ -15,10 +16,31 @@ tags:
   <a href="https://cookbook.openai.com/topic/gpt-oss"><strong>Guides</strong></a> ·
   <a href="https://openai.com/index/gpt-oss-model-card"><strong>Model card</strong></a> ·
   <a href="https://openai.com/index/introducing-gpt-oss/"><strong>OpenAI blog</strong></a>
 </p>
-<b><i><p align="center"> This model uses Git-LFS </p><b></i></b>
-<br>
 Welcome to the gpt-oss series, [OpenAI’s open-weight models](https://openai.com/open-models) designed for powerful reasoning, agentic tasks, and versatile developer use cases.
 We’re releasing two flavors of these open models:
@@ -165,4 +187,4 @@ The gpt-oss models are excellent for:
 Both gpt-oss models can be fine-tuned for a variety of specialized use cases.
-This smaller model `gpt-oss-20b` can be fine-tuned on consumer hardware, whereas the larger [`gpt-oss-120b`](https://huggingface.co/openai/gpt-oss-120b) can be fine-tuned on a single H100 node.

 library_name: transformers
 tags:
 - vllm
+- LFS
 ---
 <p align="center">
   <a href="https://cookbook.openai.com/topic/gpt-oss"><strong>Guides</strong></a> ·
   <a href="https://openai.com/index/gpt-oss-model-card"><strong>Model card</strong></a> ·
   <a href="https://openai.com/index/introducing-gpt-oss/"><strong>OpenAI blog</strong></a>
+<div align="center">
+  <blockquote>
+<p align="center">
+  <strong> Important Note: Migration to Git LFS </strong>
+  <br><br>
 </p>
+<p>
+  Previously, the weights for the <code>openai/gpt-oss-20b</code> model were hosted on <strong>Xet storage</strong>, which led to frequent download errors, such as:
+</p>
+<p align="center">
+```bash
+RuntimeError: Data processing error: CAS service error : IO Error: Timer expired (os error 62)
+````
+</p>
+<p>
+  To resolve this issue, we've migrated all model weights to <strong>Git LFS</strong>.
+</p>
+</blockquote>
+</div>
 Welcome to the gpt-oss series, [OpenAI’s open-weight models](https://openai.com/open-models) designed for powerful reasoning, agentic tasks, and versatile developer use cases.
 We’re releasing two flavors of these open models:
 Both gpt-oss models can be fine-tuned for a variety of specialized use cases.
+This smaller model `gpt-oss-20b` can be fine-tuned on consumer hardware, whereas the larger [`gpt-oss-120b`](https://huggingface.co/openai/gpt-oss-120b) can be fine-tuned on a single H100 node.