Instructions to use allenai/OLMo-2-1124-13B-Instruct-RLVR1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allenai/OLMo-2-1124-13B-Instruct-RLVR1 with Transformers:

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

pipe = pipeline("text-generation", model="allenai/OLMo-2-1124-13B-Instruct-RLVR1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-2-1124-13B-Instruct-RLVR1")
model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-1124-13B-Instruct-RLVR1")
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 allenai/OLMo-2-1124-13B-Instruct-RLVR1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allenai/OLMo-2-1124-13B-Instruct-RLVR1"
# 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-2-1124-13B-Instruct-RLVR1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/allenai/OLMo-2-1124-13B-Instruct-RLVR1

SGLang

How to use allenai/OLMo-2-1124-13B-Instruct-RLVR1 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-2-1124-13B-Instruct-RLVR1" \
    --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-2-1124-13B-Instruct-RLVR1",
		"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-2-1124-13B-Instruct-RLVR1" \
        --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-2-1124-13B-Instruct-RLVR1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use allenai/OLMo-2-1124-13B-Instruct-RLVR1 with Docker Model Runner:
```
docker model run hf.co/allenai/OLMo-2-1124-13B-Instruct-RLVR1
```

vwxyzjn commited on Jan 6, 2025

Commit

324c0d1

verified ·

1 Parent(s): 501567d

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ Upon the initial release of OLMo-2 models, we realized the post-trained models d
 ## Release Documentation
-OLMo 2 13B Instruct RLVR 1 November 2024 is post-trained variant of the [OLMo-2 13B November 2024](https://huggingface.co/allenai/OLMo2-7B-1124) model, which has undergone supervised finetuning on an OLMo-specific variant of the [Tülu 3 dataset](allenai/tulu-3-sft-olmo-2-mixture) and further DPO training on [this dataset](https://huggingface.co/datasets/allenai/olmo-2-1124-13b-preference-mix), and finally RLVR training using [this data](https://huggingface.co/datasets/allenai/RLVR-GSM-MATH_IF_Mixed-Constraints).
 Tülu 3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval.
 Check out the [OLMo 2 paper](https://arxiv.org/abs/2501.00656) or [Tülu 3 paper](https://arxiv.org/abs/2411.15124) for more details!

 ## Release Documentation
+OLMo 2 13B Instruct RLVR 1 November 2024 is post-trained variant of the [OLMo-2 13B November 2024](https://huggingface.co/allenai/OLMo2-7B-1124) model, which has undergone supervised finetuning on an OLMo-specific variant of the [Tülu 3 dataset](https://huggingface.co/datasets/allenai/tulu-3-sft-olmo-2-mixture) and further DPO training on [this dataset](https://huggingface.co/datasets/allenai/olmo-2-1124-13b-preference-mix), and finally RLVR training using [this data](https://huggingface.co/datasets/allenai/RLVR-GSM-MATH_IF_Mixed-Constraints).
 Tülu 3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval.
 Check out the [OLMo 2 paper](https://arxiv.org/abs/2501.00656) or [Tülu 3 paper](https://arxiv.org/abs/2411.15124) for more details!