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

Libraries

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

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

pipe = pipeline("text-generation", model="allenai/Olmo-3-7B-Instruct")
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")
model = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-7B-Instruct")
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

Update inference examples to use the correct chat template

by mario-sanz - opened Nov 27, 2025

base: refs/heads/main

←

from: refs/pr/7

Discussion Files changed

-8

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -45,13 +45,13 @@ You can use OLMo with the standard HuggingFace transformers library:
 from transformers import AutoModelForCausalLM, AutoTokenizer
 olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-7B-Instruct")
 tokenizer = AutoTokenizer.from_pretrained("allenai/Olmo-3-7B-Instruct")
-message = ["Who would win in a fight - a dinosaur or a cow named Moo Moo?"]
-inputs = tokenizer(message, return_tensors='pt', return_token_type_ids=False)
 # optional verifying cuda
 # inputs = {k: v.to('cuda') for k,v in inputs.items()}
 # olmo = olmo.to('cuda')
 response = olmo.generate(**inputs, max_new_tokens=100, do_sample=True, top_k=50, top_p=0.95)
-print(tokenizer.batch_decode(response, skip_special_tokens=True)[0])
 >> 'This is a fun and imaginative question! Let’s break it down...'
 ```
@@ -184,8 +184,8 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto",
 )
-prompt = "Who would win in a fight - a dinosaur or a cow named MooMoo?"
-inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 outputs = model.generate(
     **inputs,
@@ -194,7 +194,7 @@ outputs = model.generate(
     max_new_tokens=32768,
 )
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 ### vllm Example
@@ -210,8 +210,8 @@ sampling_params = SamplingParams(
     max_tokens=32768,
 )
-prompt = "Who would win in a fight - a dinosaur or a cow named MooMoo?"
-outputs = llm.generate(prompt, sampling_params)
 print(outputs[0].outputs[0].text)
 ```

 from transformers import AutoModelForCausalLM, AutoTokenizer
 olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-7B-Instruct")
 tokenizer = AutoTokenizer.from_pretrained("allenai/Olmo-3-7B-Instruct")
+message = [{"role": "user", "content": "Who would win in a fight - a dinosaur or a cow named Moo Moo?"}]
+inputs = tokenizer.apply_chat_template(message, add_generation_prompt=True, return_tensors='pt', return_dict=True)
 # optional verifying cuda
 # inputs = {k: v.to('cuda') for k,v in inputs.items()}
 # olmo = olmo.to('cuda')
 response = olmo.generate(**inputs, max_new_tokens=100, do_sample=True, top_k=50, top_p=0.95)
+print(tokenizer.decode(response[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
 >> 'This is a fun and imaginative question! Let’s break it down...'
 ```
     device_map="auto",
 )
+message = [{"role": "user", "content": "Who would win in a fight - a dinosaur or a cow named Moo Moo?"}]
+inputs = tokenizer.apply_chat_template(message, add_generation_prompt=True, return_tensors='pt', return_dict=True).to(model.device)
 outputs = model.generate(
     **inputs,
     max_new_tokens=32768,
 )
+print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
 ```
 ### vllm Example
     max_tokens=32768,
 )
+message = [{"role": "user", "content": "Who would win in a fight - a dinosaur or a cow named Moo Moo?"}]
+outputs = llm.chat(message, sampling_params)
 print(outputs[0].outputs[0].text)
 ```