Instructions to use allenai/OLMo-2-0425-1B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allenai/OLMo-2-0425-1B-SFT with Transformers:

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

pipe = pipeline("text-generation", model="allenai/OLMo-2-0425-1B-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-2-0425-1B-SFT")
model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-0425-1B-SFT")
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-2-0425-1B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allenai/OLMo-2-0425-1B-SFT"
# 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-2-0425-1B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/allenai/OLMo-2-0425-1B-SFT

SGLang

How to use allenai/OLMo-2-0425-1B-SFT 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-2-0425-1B-SFT" \
    --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-2-0425-1B-SFT",
		"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-2-0425-1B-SFT" \
        --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-2-0425-1B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use allenai/OLMo-2-0425-1B-SFT with Docker Model Runner:
```
docker model run hf.co/allenai/OLMo-2-0425-1B-SFT
```

StefanHex commited on Feb 3

Commit

2a1f1f8

verified ·

1 Parent(s): 0d85a3d

Remove note about checkpoints (only exist for RLVR)

Browse files

Intermediate checkpoints only (seem to) exist for the RLVR1 model (which makes sense given it says RL training checkpoints).

```python
olmo_model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-0425-1B-SFT", revision="step_200")
```
will fail with
```
OSError: step_200 is not a valid git identifier (branch name, tag name or commit id) that exists for this model name. Check the model page at 'https://huggingface.co/allenai/OLMo-2-0425-1B-SFT' for available revisions.
```

Files changed (1) hide show

README.md +0 -9

README.md CHANGED Viewed

@@ -77,15 +77,6 @@ I'm just a computer program, so I don't have feelings, but I'm functioning as ex
 ```
 It is embedded within the tokenizer as well, for `tokenizer.apply_chat_template`.
-### Intermediate Checkpoints
-To facilitate research on RL finetuning, we have released our intermediate checkpoints during the model's RLVR training.
-The model weights are saved every 20 training steps, and can be accessible in the revisions of the HuggingFace repository.
-For example, you can load with:
-```
-olmo_model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-0425-1B-SFT", revision="step_200")
-```
 ### Bias, Risks, and Limitations
 The OLMo-2 models have limited safety training, but are not deployed automatically with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).

 ```
 It is embedded within the tokenizer as well, for `tokenizer.apply_chat_template`.
 ### Bias, Risks, and Limitations
 The OLMo-2 models have limited safety training, but are not deployed automatically with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).