mlx-community
/

QED-Nano-8bit

Text Generation

8-bit precision

Model card Files Files and versions

abalogh commited on 22 days ago

Commit

980adf7

·

verified ·

1 Parent(s): 5c6875c

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -11,9 +11,9 @@ tags:
 - mlx
 ---
-# abalogh/QED-Nano-8bit
-This model [abalogh/QED-Nano-8bit](https://huggingface.co/abalogh/QED-Nano-8bit) was
 converted to MLX format from [lm-provers/QED-Nano](https://huggingface.co/lm-provers/QED-Nano)
 using mlx-lm version **0.29.1**.
@@ -26,7 +26,7 @@ pip install mlx-lm
 ```python
 from mlx_lm import load, generate
-model, tokenizer = load("abalogh/QED-Nano-8bit")
 prompt = "hello"

 - mlx
 ---
+# mlx-community/QED-Nano-8bit
+This model [mlx-community/QED-Nano-8bit](https://huggingface.co/mlx-community/QED-Nano-8bit) was
 converted to MLX format from [lm-provers/QED-Nano](https://huggingface.co/lm-provers/QED-Nano)
 using mlx-lm version **0.29.1**.
 ```python
 from mlx_lm import load, generate
+model, tokenizer = load("mlx-community/QED-Nano-8bit")
 prompt = "hello"