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
```

Add Artificial Analysis evaluations for olmo-3-7b-instruct

by SeasonalFall84 - opened Dec 3, 2025

base: refs/heads/main

←

from: refs/pr/8

Discussion Files changed

+51

-0

Files changed (1) hide show

README.md +51 -0

README.md CHANGED Viewed

@@ -6,6 +6,57 @@ language:
 library_name: transformers
 datasets:
 - allenai/Dolci-Instruct-RL-7B
 ---
 ## Model Details

 library_name: transformers
 datasets:
 - allenai/Dolci-Instruct-RL-7B
+model-index:
+- name: Olmo-3-7B-Instruct
+  results:
+  - task:
+      type: evaluation
+    dataset:
+      name: Artificial Analysis Benchmarks
+      type: artificial_analysis
+    metrics:
+    - name: Artificial Analysis Intelligence Index
+      type: artificial_analysis_intelligence_index
+      value: 22.2
+    - name: Artificial Analysis Coding Index
+      type: artificial_analysis_coding_index
+      value: 12.3
+    - name: Artificial Analysis Math Index
+      type: artificial_analysis_math_index
+      value: 41.3
+    - name: Mmlu Pro
+      type: mmlu_pro
+      value: 0.522
+    - name: Gpqa
+      type: gpqa
+      value: 0.4
+    - name: Hle
+      type: hle
+      value: 0.058
+    - name: Livecodebench
+      type: livecodebench
+      value: 0.266
+    - name: Scicode
+      type: scicode
+      value: 0.103
+    - name: Aime 25
+      type: aime_25
+      value: 0.413
+    - name: Ifbench
+      type: ifbench
+      value: 0.328
+    - name: Lcr
+      type: lcr
+      value: 0
+    - name: Terminalbench Hard
+      type: terminalbench_hard
+      value: 0
+    - name: Tau2
+      type: tau2
+      value: 0.126
+    source:
+      name: Artificial Analysis API
+      url: https://artificialanalysis.ai
 ---
 ## Model Details