Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,13 @@ tags:
|
|
| 19 |
|
| 20 |
*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.](https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview.)*
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
I simply converted it to MLX format with a quantization of 4-bits for better performance on Apple Silicon Macs (M1,M2,M3,M4 Chips).
|
| 23 |
|
| 24 |
# Alejandroolmedo/DeepScaleR-1.5B-Preview-4bit-mlx
|
|
|
|
| 19 |
|
| 20 |
*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.](https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview.)*
|
| 21 |
|
| 22 |
+
# Other Types/Sizes:
|
| 23 |
+
| Link | Type | Size| Notes |
|
| 24 |
+
|-------|-----------|-----------|-----------|
|
| 25 |
+
| [MLX] (https://huggingface.co/Alejandroolmedo/DeepScaleR-1.5B-Preview-8bit-mlx) | 8-bit | 1.90 GB | **Best Quality** |
|
| 26 |
+
| [MLX] (https://huggingface.co/Alejandroolmedo/DeepScaleR-1.5B-Preview-6bit-mlx) | 6-bit | 1.46 GB | Better Quality|
|
| 27 |
+
| [MLX] (https://huggingface.co/Alejandroolmedo/DeepScaleR-1.5B-Preview-4bit-mlx) | 4-bit | 1.01 GB | Good Quality|
|
| 28 |
+
|
| 29 |
I simply converted it to MLX format with a quantization of 4-bits for better performance on Apple Silicon Macs (M1,M2,M3,M4 Chips).
|
| 30 |
|
| 31 |
# Alejandroolmedo/DeepScaleR-1.5B-Preview-4bit-mlx
|