Instructions to use allenai/Olmo-3-7B-Instruct-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allenai/Olmo-3-7B-Instruct-DPO with Transformers:

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

pipe = pipeline("text-generation", model="allenai/Olmo-3-7B-Instruct-DPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("allenai/Olmo-3-7B-Instruct-DPO")
model = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-7B-Instruct-DPO")
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

vLLM

How to use allenai/Olmo-3-7B-Instruct-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allenai/Olmo-3-7B-Instruct-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allenai/Olmo-3-7B-Instruct-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/allenai/Olmo-3-7B-Instruct-DPO

SGLang

How to use allenai/Olmo-3-7B-Instruct-DPO 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 "allenai/Olmo-3-7B-Instruct-DPO" \
    --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": "allenai/Olmo-3-7B-Instruct-DPO",
		"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 "allenai/Olmo-3-7B-Instruct-DPO" \
        --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": "allenai/Olmo-3-7B-Instruct-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use allenai/Olmo-3-7B-Instruct-DPO with Docker Model Runner:
```
docker model run hf.co/allenai/Olmo-3-7B-Instruct-DPO
```

why publish

by kalle07 - opened Jan 6

Discussion

kalle07

Jan 6

all olmo-3-7b not that good like qwen3-7, except safety ?

why you publish?
any advantages?

dirkgr

Jan 16

There are many reasons, but the main one is this: The Olmo models are fully open, including training data, code, training procedure, WandB, and checkpoints. If you have enough GPUs, you can do the same thing we did. That means they are a great starting point for research, and lots of good research gets done on top of them.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment