prince-canuma commited on
Commit
9a41dc3
1 Parent(s): a1c9e64

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -0
README.md ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - mlx
5
+ ---
6
+
7
+ # mlx-community/CodeQwen1.5-7B-Chat-4bit
8
+ This model was converted to MLX format from [`Qwen/CodeQwen1.5-7B-Chat`]() using mlx-lm version **0.9.0**.
9
+
10
+ Model added by [Prince Canuma](https://twitter.com/Prince_Canuma).
11
+
12
+ Refer to the [original model card](https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat) for more details on the model.
13
+ ## Use with mlx
14
+
15
+ ```bash
16
+ pip install mlx-lm
17
+ ```
18
+
19
+ ```python
20
+ from mlx_lm import load, generate
21
+
22
+ model, tokenizer = load("mlx-community/CodeQwen1.5-7B-Chat-4bit")
23
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
24
+ ```