Hugging Face's logo

AlejandroOlmedo
/
DeepScaleR-1.5B-Preview-6bit-mlx

Text Generation
Transformers
Safetensors
MLX
English
qwen2
conversational
text-generation-inference
6-bit
Model card Files
xet
Community
AlejandroOlmedo commited on
Commit
7695521
·
verified ·
1 Parent(s): da389db

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -23,6 +23,12 @@ tags:
23
  <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;"/>
24
  </a>
25
 
 
 
 
 
 
 
26
 
27
  I simply converted it to MLX format with a quantization of 6-bits for better performance on Apple Silicon Macs (M1,M2,M3,M4 Chips).
28
 
 
23
  <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;"/>
24
  </a>
25
 
26
+ # Other Types/Sizes:
27
+ | Link | Type | Size| Notes |
28
+ |-------|-----------|-----------|-----------|
29
+ | [MLX] (https://huggingface.co/Alejandroolmedo/DeepScaleR-1.5B-Preview-8bit-mlx) | 8-bit | 1.90 GB | **Best Quality** |
30
+ | [MLX] (https://huggingface.co/Alejandroolmedo/DeepScaleR-1.5B-Preview-6bit-mlx) | 6-bit | 1.46 GB | Better Quality|
31
+ | [MLX] (https://huggingface.co/Alejandroolmedo/DeepScaleR-1.5B-Preview-4bit-mlx) | 4-bit | 1.01 GB | Good Quality|
32
 
33
  I simply converted it to MLX format with a quantization of 6-bits for better performance on Apple Silicon Macs (M1,M2,M3,M4 Chips).
34