README.md

---
license: mit
library_name: transformers
datasets:
- AI-MO/NuminaMath-CoT
- KbsdJames/Omni-MATH
- RUC-AIBOX/STILL-3-Preview-RL-Data
- hendrycks/competition_math
language:
- en
base_model: agentica-org/DeepScaleR-1.5B-Preview
tags:
- mlx
---

# About:

**A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular math evaluations.**

*Special thanks to Agentica for fine-tuning this version of Deepseek-R1-Distilled-Qwen-1.5B. More information about it can be found here:* 

https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview. (Base Model)

  </a>
  <a href="https://huggingface.co/agentica-org" style="margin: 2px;">
    <img alt="Hugging Face" src="https://img.shields.io/badge/Agentica-fcd022?style=for-the-badge&logo=huggingface&logoColor=000&labelColor" style="display: inline-block; vertical-align: middle;"/>
  </a>

  - Converted it to MLX format with a quantization of 4-bits for better performance on Apple Silicon Macs (M1,M2,M3,M4 Chips).
  - If you want a bigger model size for improved accuracy, see the models below.
  
# Other Types/Quants:
| Link | Type | Size| Notes |
|-------|-----------|-----------|-----------|
| [MLX] (https://huggingface.co/AlejandroOlmedo/DeepScaleR-1.5B-Preview-mlx) | Full | 3.57 GB | **Best Quality** |
| [MLX] (https://huggingface.co/AlejandroOlmedo/DeepScaleR-1.5B-Preview-8bit-mlx) | 8-bit | 1.90 GB | **Better Quality** |
| [MLX] (https://huggingface.co/AlejandroOlmedo/DeepScaleR-1.5B-Preview-6bit-mlx) | 6-bit | 1.46 GB | Good Quality|
| [MLX] (https://huggingface.co/AlejandroOlmedo/DeepScaleR-1.5B-Preview-4bit-mlx) | 4-bit | 1.01 GB | Bad Quality|



# AlejandroOlmedo/DeepScaleR-1.5B-Preview-4bit-mlx

The Model [AlejandroOlmedo/DeepScaleR-1.5B-Preview-4bit-mlx](https://huggingface.co/AlejandroOlmedo/DeepScaleR-1.5B-Preview-4bit-mlx) was converted to MLX format from [agentica-org/DeepScaleR-1.5B-Preview](https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview) using mlx-lm version **0.20.5**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("AlejandroOlmedo/DeepScaleR-1.5B-Preview-4bit-mlx")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```