Hugging Face's logo

bobig
/
Qwen2.5-14B-1M-YOYO-V2-Q6

Text Generation
MLX
Safetensors
English
Chinese
qwen2
Merge
conversational
6-bit
Model card Files
xet
Community
bobig commited on
Commit
77df026
·
verified ·
1 Parent(s): e2be0ba

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
- # bobig/Qwen2.5-14B-1M-YOYO-V2-Q5
14
 
15
- The Model [bobig/Qwen2.5-14B-1M-YOYO-V2-Q5](https://huggingface.co/bobig/Qwen2.5-14B-1M-YOYO-V2-Q5) was
16
  converted to MLX format from [YOYO-AI/Qwen2.5-14B-YOYO-latest-V2](https://huggingface.co/YOYO-AI/Qwen2.5-14B-YOYO-latest-V2)
17
  using mlx-lm version **0.21.4**.
18
 
@@ -25,7 +25,7 @@ pip install mlx-lm
25
  ```python
26
  from mlx_lm import load, generate
27
 
28
- model, tokenizer = load("bobig/Qwen2.5-14B-1M-YOYO-V2-Q5")
29
 
30
  prompt = "hello"
31
 
 
10
  - mlx
11
  ---
12
 
13
+ # bobig/Qwen2.5-14B-1M-YOYO-V2-Q6
14
 
15
+ The Model [bobig/Qwen2.5-14B-1M-YOYO-V2-Q6](https://huggingface.co/bobig/Qwen2.5-14B-1M-YOYO-V2-Q6) was
16
  converted to MLX format from [YOYO-AI/Qwen2.5-14B-YOYO-latest-V2](https://huggingface.co/YOYO-AI/Qwen2.5-14B-YOYO-latest-V2)
17
  using mlx-lm version **0.21.4**.
18
 
 
25
  ```python
26
  from mlx_lm import load, generate
27
 
28
+ model, tokenizer = load("bobig/Qwen2.5-14B-1M-YOYO-V2-Q6")
29
 
30
  prompt = "hello"
31