Hugging Face's logo

mlx-community
/
Polaris-7B-Preview-4bit

MLX
Safetensors
qwen2
4-bit precision
Model card Files Community
Felladrin commited on
Commit
35f50d6
·
verified ·
1 Parent(s): df55bdb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -7,9 +7,9 @@ tags:
7
  - mlx
8
  ---
9
 
10
- # Felladrin/Polaris-7B-Preview-mlx-4Bit
11
 
12
- The Model [Felladrin/Polaris-7B-Preview-mlx-4Bit](https://huggingface.co/Felladrin/Polaris-7B-Preview-mlx-4Bit) was converted to MLX format from [POLARIS-Project/Polaris-7B-Preview](https://huggingface.co/POLARIS-Project/Polaris-7B-Preview) using mlx-lm version **0.22.3**.
13
 
14
  ## Use with mlx
15
 
@@ -20,7 +20,7 @@ pip install mlx-lm
20
  ```python
21
  from mlx_lm import load, generate
22
 
23
- model, tokenizer = load("Felladrin/Polaris-7B-Preview-mlx-4Bit")
24
 
25
  prompt="hello"
26
 
 
7
  - mlx
8
  ---
9
 
10
+ # mlx-community/Polaris-7B-Preview-4bit
11
 
12
+ The Model [mlx-community/Polaris-7B-Preview-4bit](https://huggingface.co/mlx-community/Polaris-7B-Preview-4bit) was converted to MLX format from [POLARIS-Project/Polaris-7B-Preview](https://huggingface.co/POLARIS-Project/Polaris-7B-Preview) using mlx-lm version **0.22.3**.
13
 
14
  ## Use with mlx
15
 
 
20
  ```python
21
  from mlx_lm import load, generate
22
 
23
+ model, tokenizer = load("mlx-community/Polaris-7B-Preview-4bit")
24
 
25
  prompt="hello"
26