DeepScaleR-1.5B-Preview-4bit-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:

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

The Model AlejandroOlmedo/DeepScaleR-1.5B-Preview-4bit-mlx was converted to MLX format from agentica-org/DeepScaleR-1.5B-Preview using mlx-lm version 0.20.5.

Use with mlx

pip install mlx-lm

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)