zimengxiong commited on
Commit
fdfd42a
·
verified ·
1 Parent(s): 3f403fb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -21,7 +21,9 @@ model_relations:
21
 
22
  This is an 8-bit quantized [MLX](https://github.com/ml-explore/mlx) version of [tencent/WeDLM-8B-Instruct](https://huggingface.co/tencent/WeDLM-8B-Instruct) for efficient inference on Apple Silicon.
23
 
 
24
  https://github.com/ZimengXiong/WeDLM-MLX/tree/main
 
25
  ## Related Models
26
 
27
  | Variant | HuggingFace |
 
21
 
22
  This is an 8-bit quantized [MLX](https://github.com/ml-explore/mlx) version of [tencent/WeDLM-8B-Instruct](https://huggingface.co/tencent/WeDLM-8B-Instruct) for efficient inference on Apple Silicon.
23
 
24
+ It currently does not work too well or provide meaningfull speedup due to lack of pre compilation.
25
  https://github.com/ZimengXiong/WeDLM-MLX/tree/main
26
+
27
  ## Related Models
28
 
29
  | Variant | HuggingFace |