Hugging Face's logo

AlejandroOlmedo
/
zeta-4bit-mlx

MLX
Safetensors
qwen2
4-bit precision
Model card Files
xet
 Community
AlejandroOlmedo commited on
Commit
a75d590
·
verified ·
1 Parent(s): 8bfb450

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -24,13 +24,13 @@ I simply converted it to MLX format (using mlx-lm version **0.21.4**.) with a qu
24
  ## Other Types:
25
  | Link | Type | Size| Notes |
26
  |-------|-----------|-----------|-----------|
27
- | [MLX] (https://huggingface.co/Alejandroolmedo/zeta-8bit-mlx) | 8-bit | 8.10 GB | **Best Quality** |
28
- | [MLX] (https://huggingface.co/Alejandroolmedo/zeta-4bit-mlx) | 4-bit | 4.30 GB | Good Quality|
29
 
30
 
31
- # Alejandroolmedo/zeta-4bit-mlx
32
 
33
- The Model [Alejandroolmedo/zeta-4bit-mlx](https://huggingface.co/Alejandroolmedo/zeta-4bit-mlx) was
34
  converted to MLX format from [zed-industries/zeta](https://huggingface.co/zed-industries/zeta)
35
  using mlx-lm version **0.21.4**.
36
 
@@ -43,7 +43,7 @@ pip install mlx-lm
43
  ```python
44
  from mlx_lm import load, generate
45
 
46
- model, tokenizer = load("Alejandroolmedo/zeta-4bit-mlx")
47
 
48
  prompt = "hello"
49
 
 
24
  ## Other Types:
25
  | Link | Type | Size| Notes |
26
  |-------|-----------|-----------|-----------|
27
+ | [MLX] (https://huggingface.co/AlejandroOlmedo/zeta-8bit-mlx) | 8-bit | 8.10 GB | **Best Quality** |
28
+ | [MLX] (https://huggingface.co/AlejandroOlmedo/zeta-4bit-mlx) | 4-bit | 4.30 GB | Good Quality|
29
 
30
 
31
+ # AlejandroOlmedo/zeta-4bit-mlx
32
 
33
+ The Model [AlejandroOlmedo/zeta-4bit-mlx](https://huggingface.co/AlejandroOlmedo/zeta-4bit-mlx) was
34
  converted to MLX format from [zed-industries/zeta](https://huggingface.co/zed-industries/zeta)
35
  using mlx-lm version **0.21.4**.
36
 
 
43
  ```python
44
  from mlx_lm import load, generate
45
 
46
+ model, tokenizer = load("AlejandroOlmedo/zeta-4bit-mlx")
47
 
48
  prompt = "hello"
49