Hugging Face's logo

ethicalabs
/
TowerInstruct-7B-v0.2-mlx-4Bit

Translation
MLX
Safetensors
llama
4-bit precision
Model card Files Community
mrs83 commited on
Commit
b243427
·
verified ·
1 Parent(s): 8d3168f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -19,9 +19,9 @@ tags:
19
  base_model: Unbabel/TowerInstruct-7B-v0.2
20
  ---
21
 
22
- # mrs83/TowerInstruct-7B-v0.2-mlx-4Bit
23
 
24
- The Model [mrs83/TowerInstruct-7B-v0.2-mlx-4Bit](https://huggingface.co/mrs83/TowerInstruct-7B-v0.2-mlx-4Bit) was converted to MLX format from [Unbabel/TowerInstruct-7B-v0.2](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.2) using mlx-lm version **0.22.1**.
25
 
26
  ## Use with mlx
27
 
@@ -32,7 +32,7 @@ pip install mlx-lm
32
  ```python
33
  from mlx_lm import load, generate
34
 
35
- model, tokenizer = load("mrs83/TowerInstruct-7B-v0.2-mlx-4Bit")
36
 
37
  prompt="hello"
38
 
 
19
  base_model: Unbabel/TowerInstruct-7B-v0.2
20
  ---
21
 
22
+ # ethicalabs/TowerInstruct-7B-v0.2-mlx-4Bit
23
 
24
+ The Model [ethicalabs/TowerInstruct-7B-v0.2-mlx-4Bit](https://huggingface.co/ethicalabs/TowerInstruct-7B-v0.2-mlx-4Bit) was converted to MLX format from [Unbabel/TowerInstruct-7B-v0.2](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.2) using mlx-lm version **0.22.1**.
25
 
26
  ## Use with mlx
27
 
 
32
  ```python
33
  from mlx_lm import load, generate
34
 
35
+ model, tokenizer = load("ethicalabs/TowerInstruct-7B-v0.2-mlx-4Bit")
36
 
37
  prompt="hello"
38