Hugging Face's logo

mlx-community
/
SWE-Fixer-Editor-72B-4bit

Text Generation
MLX
Safetensors
qwen2
code
conversational
4-bit precision
Model card Files Community
abalogh commited on
Commit
b65202d
·
verified ·
1 Parent(s): 8e805ab

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -10,9 +10,9 @@ tags:
10
  - mlx
11
  ---
12
 
13
- # abalogh/SWE-Fixer-Editor-72B-4bit
14
 
15
- The Model [abalogh/SWE-Fixer-Editor-72B-4bit](https://huggingface.co/abalogh/SWE-Fixer-Editor-72B-4bit) was
16
  converted to MLX format from [internlm/SWE-Fixer-Editor-72B](https://huggingface.co/internlm/SWE-Fixer-Editor-72B)
17
  using mlx-lm version **0.21.1**.
18
 
@@ -25,7 +25,7 @@ pip install mlx-lm
25
  ```python
26
  from mlx_lm import load, generate
27
 
28
- model, tokenizer = load("abalogh/SWE-Fixer-Editor-72B-4bit")
29
 
30
  prompt = "hello"
31
 
 
10
  - mlx
11
  ---
12
 
13
+ # mlx-community/SWE-Fixer-Editor-72B-4bit
14
 
15
+ The Model [mlx-community/SWE-Fixer-Editor-72B-4bit](https://huggingface.co/mlx-community/SWE-Fixer-Editor-72B-4bit) was
16
  converted to MLX format from [internlm/SWE-Fixer-Editor-72B](https://huggingface.co/internlm/SWE-Fixer-Editor-72B)
17
  using mlx-lm version **0.21.1**.
18
 
 
25
  ```python
26
  from mlx_lm import load, generate
27
 
28
+ model, tokenizer = load("mlx-community/SWE-Fixer-Editor-72B-4bit")
29
 
30
  prompt = "hello"
31