DeepScaleR-1.5B is a highly optimized language model designed to enhance problem-solving and reasoning through advanced reinforcement learning techniques. Built on a strong computational foundation, it efficiently scales to handle long-context tasks with improved accuracy. By leveraging a structured reward system and iterative context expansion, DeepScaleR demonstrates significant performance gains in mathematical reasoning and structured problem-solving. Developed with open collaboration in mind, it is released under the MIT License, allowing researchers and developers to explore, modify, and contribute to its ongoing improvements.
| Model | AIME 2024 | MATH 500 | AMC 2023 | Minerva Math | OlympiadBench | Avg. |
|---|
| 2.5-7B-Instruct | 13.3 | 79.8 | 50.6 | 34.6 | 40.7 | 43.8 |
| rStar-Math-7B | 26.7 | 78.4 | 47.5 | – | 47.1 | – |
| Eurus-2-7B-PRIME | 26.7 | 79.2 | 57.8 | 38.6 | 42.1 | 48.9 |
| Qwen2.5-7B-SimpleRL | 26.7 | 82.4 | 62.5 | 39.7 | 43.3 | 50.9 |
| DeepSeek-R1-Distill-Qwen-1.5B | 28.8 | 82.8 | 62.9 | 26.5 | 43.3 | 48.9 |
| Still-1.5B | 32.5 | 84.4 | 66.7 | 29.0 | 45.4 | 51.6 |
| DeepScaleR-1.5B-Preview | 43.1 | 87.8 | 73.6 | 30.2 | 50.0 | 57.0 |
| O1-Preview | 40.0 | 81.4 | – | – | – | – |
Model Resource
Hugging Face
Link: https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview
Ollama
Link: https://ollama.com/library/deepscaler
Prerequisites for Running DeepScaler 1.5B Locally
- VRAM:
- Minimum: 16GB for 8-bit or 4-bit quantization.
- Recommended: 24GB for smoother inference and lightweight fine-tuning.
- Optimal: 48GB+ for full-precision training and inference.
- Disk Space:
- Minimum: 30GB for storing model weights and temporary files.
- Recommended: 100GB for additional datasets and fine-tuning outputs.
- RAM:
- Minimum: 16GB for running inference.
- Recommended: 32GB for smoother execution.
- CPU:
- Minimum: 8 cores.
- Recommended: 16–32 cores for faster data preprocessing and multitasking.
- Storage Type:
- Use SSD for faster read/write speeds, ensuring faster model loading and data handling.
Performance Summary
- RTX 3090/4090:
- Best for inference with 8-bit quantization.
- Handles inference smoothly for shorter context lengths.
- RTX A6000:
- Handles full-precision inference for context lengths up to 16K tokens.
- A100 40GB/80GB:
- Excels at fine-tuning and long-context inference.
- H100 80GB:
- Ideal for resource-heavy multi-step tasks, long-context inference, and high-throughput fine-tuning.
Multi-GPU Scaling
For faster inference or fine-tuning, consider multi-GPU setups:
- 2x RTX A6000 for efficient fine-tuning.
- 4x A100 40GB for large-scale tasks.
Step-by-Step Process to Run DeepScaler 1.5B Model Locally
For the purpose of this tutorial, we will use a GPU-powered Virtual Machine offered by NodeShift; however, you can replicate the same steps with any other cloud provider of your choice. NodeShift provides the most affordable Virtual Machines at a scale that meets GDPR, SOC2, and ISO27001 requirements.
Step 1: Sign Up and Set Up a NodeShift Cloud Account
Visit the NodeShift Platform and create an account. Once you’ve signed up, log into your account.
Follow the account setup process and provide the necessary details and information.
Step 2: Create a GPU Node (Virtual Machine)
GPU Nodes are NodeShift’s GPU Virtual Machines, on-demand resources equipped with diverse GPUs ranging from H100s to A100s. These GPU-powered VMs provide enhanced environmental control, allowing configuration adjustments for GPUs, CPUs, RAM, and Storage based on specific requirements.
Navigate to the menu on the left side. Select the GPU Nodes option, create a GPU Node in the Dashboard, click the Create GPU Node button, and create your first Virtual Machine deployment.
Step 3: Select a Model, Region, and Storage
In the “GPU Nodes” tab, select a GPU Model and Storage according to your needs and the geographical region where you want to launch your model.
We will use 1x RTX A6000 GPU for this tutorial to achieve the fastest performance. However, you can choose a more affordable GPU with less VRAM if that better suit your requirements.
Step 4: Select Authentication Method
There are two authentication methods available: Password and SSH Key. SSH keys are a more secure option. To create them, please refer to our official documentation.
Step 5: Choose an Image
Next, you will need to choose an image for your Virtual Machine. We will deploy DeepScaler 1.5B on an NVIDIA Cuda Virtual Machine. This proprietary, closed-source parallel computing platform will allow you to install DeepScaler 1.5B on your GPU Node.
After choosing the image, click the ‘Create’ button, and your Virtual Machine will be deployed.
Step 6: Virtual Machine Successfully Deployed
You will get visual confirmation that your node is up and running.
Step 7: Connect to GPUs using SSH
NodeShift GPUs can be connected to and controlled through a terminal using the SSH key provided during GPU creation.
Once your GPU Node deployment is successfully created and has reached the ‘RUNNING’ status, you can navigate to the page of your GPU Deployment Instance. Then, click the ‘Connect’ button in the top right corner.
Now open your terminal and paste the proxy SSH IP or direct SSH IP.
Next, if you want to check the GPU details, run the command below:
nvidia-smi
Step 8: Install Ollama
After connecting to the terminal via SSH, it’s now time to install Ollama from the official Ollama website.
Website Link: https://ollama.com/
Run the following command to install the Ollama:
curl -fsSL https://ollama.com/install.sh | sh
Step 9: Serve Ollama
Run the following command to host the Ollama so that it can be accessed and utilized efficiently:
ollama serve
Now, “Ollama is running.”
Step 10: Select DeepScaler 1.5B Model
Link: https://ollama.com/library/deepscaler:1.5b
DeepScaler model is available in only one size: 1.5B. We will run it on our GPU virtual machine.
Step 11: Connect with SSH
Now, open a new tab in the terminal and reconnect using SSH.
Step 12: Check Commands
Run, the following command to see a list of available commands:
Step 13: Check Available Models
Run the following command to check if the downloaded model are available:
ollama list
Step 14: Pull DeepScaler 1.5B Model
Run the following command to pull the DeepScaler 1.5B model:
ollama pull deepscaler:1.5b
Step 15: Run DeepScaler 1.5B Model
Now, you can run the model in the terminal using the following command and interact with your model:
ollama run deepscaler:1.5b
Note: This is a step-by-step guide for interacting with your model. It covers the first method for installing SmallThinker locally using Ollama and running it in the terminal.
Option 1: Using Ollama (Terminal)
- Install Ollama: Download and install the Ollama tool from the official site.
- Pull the Model: Run the following command to download the desired model:
ollama pull deepscaler:1.5b
- Run the Model: Start the model in the terminal:
ollama run deepscaler:1.5b
Option 2: Using Open WebUI
- Set Up Open WebUI:
Follow our Open WebUI Setup Guide to configure the interface. Ensure all dependencies are installed and the environment is correctly set up.
- Refresh the Interface:
Confirm that the DeepScaler 1.5B model has been downloaded and is visible in the list of available models on the Open WebUI.
- Select Your Model:
Choose the DeepScaler 1.5B model from the list. This model is available in a single size.
- Start Interaction:
Begin using the model by entering your queries in the interface.
Option 3: Using Hugging Face and Jupyter Notebook
- Follow our Jupyter Notebook Setup Guide to configure your notebook environment. Ensure that all required dependencies are installed and that your Jupyter Notebook is set up correctly for optimal use.
When choosing an image for your Virtual Machine, select the Jupyter Notebook image. This open-source platform allows you to install and run the DeepScaler 1.5B model on your GPU node. By running this model on a Jupyter Notebook, you can avoid using the terminal, simplifying the process and reducing setup time. This approach enables you to configure the model in just a few steps and minutes.
Note: NodeShift provides multiple image template options, such as TensorFlow, PyTorch, NVIDIA CUDA, Deepo, Whisper ASR Webservice, and Jupyter Notebook. With these options, you don’t need to install additional libraries or packages to run Jupyter Notebook. You can start Jupyter Notebook in just a few simple clicks.
Link: https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview
System Configuration Summary
After setting up the VM and running your Jupyter Notebook, start installing the DeepScaler 1.5B model.
Step 1: Open Jupyter Notebook
- Start Jupyter Notebook on your GPU VM.
- Open a new Python notebook.
Step 2: Install Required Dependencies
Run the following commands in a Jupyter Notebook cell to install necessary dependencies:
!pip install torch transformers safetensors vllm huggingface_hub accelerate bitsandbytes
Step 3: Import Required Libraries
After installation, import the required libraries:
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
Step 4: Load the Model and Tokenizer
Use the Hugging Face Hub to load the DeepScaleR-1.5B model:
model_name = "agentica-org/DeepScaleR-1.5B-Preview"
# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Load model with optimized settings for GPU
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16, # Use mixed precision for performance
device_map="auto" # Automatically map model to available GPU
)
Step 5: Run Inference Using the Model
Now, you can generate text using the model. Run the following cell:
# Define the input prompt
prompt = "Solve the math problem: What is the sum of angles in a triangle?"
# Tokenize input
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
# Generate output
output = model.generate(**inputs, max_new_tokens=100)
# Decode and print the response
response = tokenizer.decode(output[0], skip_special_tokens=True)
print(response)
Step 6: Using the Model with a Pipeline
If you want to use a simpler pipeline for text generation:
# Load model pipeline
generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0)
# Generate response
response = generator(prompt, max_new_tokens=100)
print(response[0]['generated_text'])
Step 7: Save and Export the Results
To save model output in a text file:
with open("deepscaler_output.txt", "w") as file:
file.write(response[0]['generated_text'])
Step 8: Fine-tuning or Further Training (Optional)
If you want to fine-tune DeepScaleR-1.5B on your dataset, you need PEFT (Parameter Efficient Fine-Tuning) or LoRA. Run:
!pip install peft
from peft import get_peft_model, LoraConfig, TaskType
lora_config = LoraConfig(
task_type=TaskType.CAUSAL_LM,
r=8,
lora_alpha=32,
lora_dropout=0.1
)
peft_model = get_peft_model(model, lora_config)
You’re all set to use DeepScaler 1.5B model! 🚀
Conclusion
DeepScaleR-1.5B is a powerful language model built for efficient problem-solving and long-context reasoning. By leveraging structured reinforcement learning and iterative training improvements, it achieves impressive accuracy in mathematical and structured tasks. With its open-source availability under the MIT License, researchers and developers can freely experiment, optimize, and expand its capabilities. Whether running on local hardware or cloud-based GPU setups, DeepScaleR offers a scalable and efficient solution for tackling complex computational challenges.
