Instructions to use dakopi/olmo3-7b_data-repetition with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dakopi/olmo3-7b_data-repetition with Transformers:

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

pipe = pipeline("text-generation", model="dakopi/olmo3-7b_data-repetition")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dakopi/olmo3-7b_data-repetition")
model = AutoModelForCausalLM.from_pretrained("dakopi/olmo3-7b_data-repetition", device_map="auto")
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 dakopi/olmo3-7b_data-repetition with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dakopi/olmo3-7b_data-repetition"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dakopi/olmo3-7b_data-repetition",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dakopi/olmo3-7b_data-repetition

SGLang

How to use dakopi/olmo3-7b_data-repetition 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 "dakopi/olmo3-7b_data-repetition" \
    --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": "dakopi/olmo3-7b_data-repetition",
		"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 "dakopi/olmo3-7b_data-repetition" \
        --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": "dakopi/olmo3-7b_data-repetition",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dakopi/olmo3-7b_data-repetition with Docker Model Runner:
```
docker model run hf.co/dakopi/olmo3-7b_data-repetition
```

olmo3-7b_data-repetition / README.md

dakopi

Update README.md

e577d06 verified 5 months ago

preview code

Raw

History Blame Contribute Delete

1.9 kB

	---
	license: apache-2.0
	base_model: allenai/Olmo-3-1025-7B
	language:
	- en
	library_name: transformers
	---


	This repo is a collection of SFT checkpoints produced by sweeping unique training samples vs epochs, following the setup from the paper:

	Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning
	https://arxiv.org/abs/2602.11149



	### Default model

	The repo root contains the weights and config for the default variant trained with 16 epochs on 800 samples.
	Calling `from_pretrained(repo_id)` loads this checkpoint.

	### Variants

	Each subfolder follows:

	s{N}_e{M}

	where:
	- s{N} means N unique samples
	- e{M} means M epochs

	Example names:
	- s3200_e8 means 3200 unique samples trained for 8 epochs
	- s12800_e1 means 12800 unique samples trained for 1 epoch

	## How to load

	Load the default model (root):

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	repo_id = "dakopi/olmo3-7b_data-repetition"

	tokenizer = AutoTokenizer.from_pretrained(repo_id)
	model = AutoModelForCausalLM.from_pretrained(repo_id)
	```

	Load a specific variant (subfolder):

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	repo_id = "dakopi/olmo3-7b_data-repetition"
	variant = "s6400_e4"

	tokenizer = AutoTokenizer.from_pretrained(repo_id, subfolder=variant)
	model = AutoModelForCausalLM.from_pretrained(repo_id, subfolder=variant)
	```


	## Reproducibility and code

	Official training and evaluation code:
	https://github.com/dkopi/data-repetition

	## Citation

	```
	@misc{kopiczko2026datarepetitionbeatsdata,
	title = {Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning},
	author = {Dawid J. Kopiczko and Sagar Vaze and Tijmen Blankevoort and Yuki M. Asano},
	year = {2026},
	eprint = {2602.11149},
	archivePrefix= {arXiv},
	primaryClass = {cs.CL},
	url = {https://arxiv.org/abs/2602.11149}
	}
	```