Instructions to use Harvard-DCML/boomerang-qwen3-2.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Harvard-DCML/boomerang-qwen3-2.3B with Transformers:

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

pipe = pipeline("text-generation", model="Harvard-DCML/boomerang-qwen3-2.3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Harvard-DCML/boomerang-qwen3-2.3B")
model = AutoModelForCausalLM.from_pretrained("Harvard-DCML/boomerang-qwen3-2.3B")
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

vLLM

How to use Harvard-DCML/boomerang-qwen3-2.3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Harvard-DCML/boomerang-qwen3-2.3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Harvard-DCML/boomerang-qwen3-2.3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Harvard-DCML/boomerang-qwen3-2.3B

SGLang

How to use Harvard-DCML/boomerang-qwen3-2.3B 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 "Harvard-DCML/boomerang-qwen3-2.3B" \
    --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": "Harvard-DCML/boomerang-qwen3-2.3B",
		"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 "Harvard-DCML/boomerang-qwen3-2.3B" \
        --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": "Harvard-DCML/boomerang-qwen3-2.3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Harvard-DCML/boomerang-qwen3-2.3B with Docker Model Runner:
```
docker model run hf.co/Harvard-DCML/boomerang-qwen3-2.3B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Description

Boomerang distillation is a phenomenon in LLMs that allows us to distill a teacher model into a student and reincorporate teacher layers to create intermediate-sized models with no additional training. This is the student model distilled from Qwen3-4B-Base from our paper.

Training Procedure

This model was initialized from Qwen3-4B-Base by copying every other layer and the last 2 layers. It was distilled on 2.1B tokens of The Pile deduplicated with cross entropy, KL, and cosine loss to match the activations of Qwen3-4B-Base. We used the following hyperparameters:

Learning rate: 3e-4
Learning rate scheduler: cosine
Warmup ratio: 0.01
Optimizer: AdamW
Adam betas: (0.9, 0.95)
Adam epsilon: 1e-8
Weight decay: 0.1
Max. gradient norm: 1.0
Number of training steps: 500
Max. sequence length: 2048
Effective batch size: 2048
Mixed precision: bf16
KLDiv weight: 0.1
Cosine distance weight per layer: 0.1

Use

To interpolate between this model and Qwen3-4B-Base, please use the build_intermediate_model function from our github repository:

import torch
from patching.patch import build_intermediate_model

intermediate_model = build_intermediate_model(
  teacher_name_or_path = "Qwen/Qwen3-4B-Base",
  student_name_or_path = "Harvard-DCML/boomerang-qwen3-2.3B",
  num_layers_to_patch = 2,
  patch_first_k_layers = False,
  dtype = torch.bfloat16,
)

Notes:

Changing num_layers_to_patch changes the size of the intermediate model by patching different numbers of student layers.
patch_first_k_layers should be set to False for this model for optimal interpolation performance.

Citation

@article{kangaslahti2025boomerang,
  title={Boomerang Distillation Enables Zero-Shot Model Size Interpolation},
  author={Kangaslahti, Sara and Nayak, Nihal V and Geuter, Jonathan and Fumero, Marco and Locatello, Francesco and Alvarez-Melis, David},
  journal={arXiv preprint arXiv:2510.05064},
  year={2025},
  url={https://arxiv.org/abs/2510.05064}
}