Instructions to use ValiantLabs/gpt-oss-20b-Esper3.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ValiantLabs/gpt-oss-20b-Esper3.1 with Transformers:

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

pipe = pipeline("text-generation", model="ValiantLabs/gpt-oss-20b-Esper3.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ValiantLabs/gpt-oss-20b-Esper3.1")
model = AutoModelForMultimodalLM.from_pretrained("ValiantLabs/gpt-oss-20b-Esper3.1")
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 ValiantLabs/gpt-oss-20b-Esper3.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ValiantLabs/gpt-oss-20b-Esper3.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ValiantLabs/gpt-oss-20b-Esper3.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ValiantLabs/gpt-oss-20b-Esper3.1

SGLang

How to use ValiantLabs/gpt-oss-20b-Esper3.1 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 "ValiantLabs/gpt-oss-20b-Esper3.1" \
    --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": "ValiantLabs/gpt-oss-20b-Esper3.1",
		"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 "ValiantLabs/gpt-oss-20b-Esper3.1" \
        --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": "ValiantLabs/gpt-oss-20b-Esper3.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ValiantLabs/gpt-oss-20b-Esper3.1 with Docker Model Runner:
```
docker model run hf.co/ValiantLabs/gpt-oss-20b-Esper3.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Support our open-source dataset and model releases!

Esper 3.1: Ministral-3-3B-Reasoning-2512, Qwen3-4B-Thinking-2507, Ministral-3-8B-Reasoning-2512, Ministral-3-14B-Reasoning-2512, gpt-oss-20b, Qwen3.5-27B, Qwen3.6-27B, Qwen3.6-35B-A3B

Esper 3.1 is a coding, architecture, and DevOps reasoning specialist built on gpt-oss.

Your dedicated DevOps expert: Esper 3.1 maximizes DevOps and architecture helpfulness, powered by high-difficulty DevOps and architecture data generated with DeepSeek-V3.1-Terminus!
Improved coding performance: challenging code-reasoning datasets stretch DeepSeek-V3.1-Terminus and DeepSeek-V3.2 to the limits, allowing Esper 3.1 to tackle harder coding tasks!
AI to build AI: our high-difficulty AI expertise data boosts Esper 3.1's MLOps, AI architecture, AI research, and general reasoning skills.
Small model sizes allow running on local desktop and mobile, plus super-fast server inference!

Prompting Guide

Esper 3.1 uses the gpt-oss-20b prompt format.

Esper 3.1 is a reasoning finetune; reasoning level high is generally recommended.

NOTE: This release of Esper 3.1 uses bf16 for all parameters. Consider quantized models if you're not looking to use bf16.

Example inference script provided by gpt-oss-20b to get started:

from transformers import pipeline
import torch

model_id = "ValiantLabs/gpt-oss-20b-Esper3.1"

pipe = pipeline(
    "text-generation",
    model=model_id,
    torch_dtype="auto",
    device_map="auto",
)

messages = [
    {"role": "user", "content": "Design a serverless architecture for a real-time image processing application using AWS Lambda and Amazon S3."},
]

outputs = pipe(
    messages,
    max_new_tokens=15000,
)
print(outputs[0]["generated_text"][-1])