Hugging Face's logo

mlx-community
/
aya-expanse-8b-4bit

Text Generation
Transformers
Safetensors
MLX
cohere
conversational
text-generation-inference
4-bit precision
Model card Files Community
1
datageek commited on
Commit
3a7cee3
•
1 Parent(s): c656a9d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -41,9 +41,9 @@ tags:
41
  - mlx
42
  ---
43
 
44
- # mlx-community/aya-expanse-8b
45
 
46
- The Model [mlx-community/aya-expanse-8b](https://huggingface.co/mlx-community/aya-expanse-8b) was converted to MLX format from [CohereForAI/aya-expanse-8b](https://huggingface.co/CohereForAI/aya-expanse-8b) using mlx-lm version **0.19.1**.
47
 
48
  ## Use with mlx
49
 
@@ -54,7 +54,7 @@ pip install mlx-lm
54
  ```python
55
  from mlx_lm import load, generate
56
 
57
- model, tokenizer = load("mlx-community/aya-expanse-8b")
58
 
59
  prompt="hello"
60
 
 
41
  - mlx
42
  ---
43
 
44
+ # mlx-community/aya-expanse-8b-4bit
45
 
46
+ The Model [mlx-community/aya-expanse-8b-4bit](https://huggingface.co/mlx-community/aya-expanse-8b) was converted to MLX format from [CohereForAI/aya-expanse-8b](https://huggingface.co/CohereForAI/aya-expanse-8b) using mlx-lm version **0.19.1**.
47
 
48
  ## Use with mlx
49
 
 
54
  ```python
55
  from mlx_lm import load, generate
56
 
57
+ model, tokenizer = load("mlx-community/aya-expanse-8b-4bit")
58
 
59
  prompt="hello"
60