|
|
--- |
|
|
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 8-bits for better performance on Apple Silicon Macs (M1,M2,M3,M4 Chips). |
|
|
- If you want a bigger model size for improved accuracy or smaller size for performance, 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-8bit-mlx |
|
|
|
|
|
The Model [AlejandroOlmedo/DeepScaleR-1.5B-Preview-8bit-mlx](https://huggingface.co/AlejandroOlmedo/DeepScaleR-1.5B-Preview-8bit-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-8bit-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) |
|
|
``` |
|
|
|
