Hugging Face's logo

mlx-community
/
SmallThinker-3B-Preview-4bit

Text Generation
Transformers
Safetensors
MLX
English
qwen2
conversational
text-generation-inference
Inference Endpoints
4-bit precision
Model card Files Community
1
abalogh commited on
Commit
7675810
·
verified ·
1 Parent(s): 7dcfa5f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -11,9 +11,9 @@ tags:
11
  - mlx
12
  ---
13
 
14
- # abalogh/SmallThinker-3B-Preview-4bit
15
 
16
- The Model [abalogh/SmallThinker-3B-Preview-4bit](https://huggingface.co/abalogh/SmallThinker-3B-Preview-4bit) was
17
  converted to MLX format from [PowerInfer/SmallThinker-3B-Preview](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview)
18
  using mlx-lm version **0.20.6**.
19
 
@@ -26,7 +26,7 @@ pip install mlx-lm
26
  ```python
27
  from mlx_lm import load, generate
28
 
29
- model, tokenizer = load("abalogh/SmallThinker-3B-Preview-4bit")
30
 
31
  prompt="hello"
32
 
 
11
  - mlx
12
  ---
13
 
14
+ # mlx-community/SmallThinker-3B-Preview-4bit
15
 
16
+ The Model [mlx-community/SmallThinker-3B-Preview-4bit](https://huggingface.co/mlx-community/SmallThinker-3B-Preview-4bit) was
17
  converted to MLX format from [PowerInfer/SmallThinker-3B-Preview](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview)
18
  using mlx-lm version **0.20.6**.
19
 
 
26
  ```python
27
  from mlx_lm import load, generate
28
 
29
+ model, tokenizer = load("mlx-community/SmallThinker-3B-Preview-4bit")
30
 
31
  prompt="hello"
32