Instructions to use Harvard-DCML/ADAPT-Olmo3-4.3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Harvard-DCML/ADAPT-Olmo3-4.3B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Harvard-DCML/ADAPT-Olmo3-4.3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Harvard-DCML/ADAPT-Olmo3-4.3B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Harvard-DCML/ADAPT-Olmo3-4.3B-Instruct", 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 Harvard-DCML/ADAPT-Olmo3-4.3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Harvard-DCML/ADAPT-Olmo3-4.3B-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": "Harvard-DCML/ADAPT-Olmo3-4.3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Harvard-DCML/ADAPT-Olmo3-4.3B-Instruct

SGLang

How to use Harvard-DCML/ADAPT-Olmo3-4.3B-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 "Harvard-DCML/ADAPT-Olmo3-4.3B-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": "Harvard-DCML/ADAPT-Olmo3-4.3B-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 "Harvard-DCML/ADAPT-Olmo3-4.3B-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": "Harvard-DCML/ADAPT-Olmo3-4.3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Harvard-DCML/ADAPT-Olmo3-4.3B-Instruct with Docker Model Runner:
```
docker model run hf.co/Harvard-DCML/ADAPT-Olmo3-4.3B-Instruct
```

Model Description

ADAPT is a technique that allows for size interpolation across different post-trained variants of the same base model. This is the student model distilled from Olmo-3-7B-Instruct from our paper.

Training Procedure

This model was initialized from Olmo-3-7B-Instruct by copying every other layer and the last 2 layers. It was distilled on 1B tokens of The deduplicated Pile and 1B of the math split from Llama Nemotron Post Training Dataset with cross entropy, KL, and cosine loss to match the activations of Olmo-3-7B-Instruct. 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 (Pre-training phase): 480
Effective batch size (Pre-training phase): 2048
Number of training steps (SFT phase): 585
Effective batch size (SFT phase): 4096
Max. sequence length: 1024
Mixed precision: bf16
KLDiv weight: 0.1
Cosine distance weight per layer: 10.0

Use

To interpolate between this model and Olmo-3-7B-Instruct, 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 = "allenai/Olmo-3-7B-Instruct",
  student_name_or_path = "Harvard-DCML/ADAPT-Olmo3-4.3B-Instruct",
  num_layers_to_patch = 2,
  patch_first_k_layers = True,
  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 True for this model for optimal interpolation performance.

Citation

@misc{zhou2026thinkingrightsizeamortized,
      title={Thinking at the Right Size: Amortized Distillation Across Post-Trained LLMs}, 
      author={Yan Zhou and Sara Kangaslahti and Jonathan Geuter and Nihal V. Nayak and Marco Fumero and Francesco Locatello and David Alvarez-Melis},
      year={2026},
      eprint={2608.22854},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2608.22854}, 
}