HF中国镜像站's logo

mlx-community
/
Qwen2.5-14B-Instruct-1M-abliterated-4bit

Text Generation
Transformers
Safetensors
MLX
English
qwen2
chat
abliterated
uncensored
mlx-my-repo
conversational
text-generation-inference
4-bit precision
Model card Files Community
Felladrin commited on
Commit
88d95c8
·
verified ·
1 Parent(s): da1f5da

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -14,9 +14,9 @@ tags:
14
  library_name: transformers
15
  ---
16
 
17
- # Felladrin/Qwen2.5-14B-Instruct-1M-abliterated-Q4-mlx
18
 
19
- The Model [Felladrin/Qwen2.5-14B-Instruct-1M-abliterated-Q4-mlx](https://huggingface.co/Felladrin/Qwen2.5-14B-Instruct-1M-abliterated-Q4-mlx) was converted to MLX format from [huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated](https://huggingface.co/huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated) using mlx-lm version **0.20.5**.
20
 
21
  ## Use with mlx
22
 
@@ -27,7 +27,7 @@ pip install mlx-lm
27
  ```python
28
  from mlx_lm import load, generate
29
 
30
- model, tokenizer = load("Felladrin/Qwen2.5-14B-Instruct-1M-abliterated-Q4-mlx")
31
 
32
  prompt="hello"
33
 
 
14
  library_name: transformers
15
  ---
16
 
17
+ # mlx-community/Qwen2.5-14B-Instruct-1M-abliterated-4bit
18
 
19
+ The Model [mlx-community/Qwen2.5-14B-Instruct-1M-abliterated-4bit](https://huggingface.co/mlx-community/Qwen2.5-14B-Instruct-1M-abliterated-4bit) was converted to MLX format from [huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated](https://huggingface.co/huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated) using mlx-lm version **0.20.5**.
20
 
21
  ## Use with mlx
22
 
 
27
  ```python
28
  from mlx_lm import load, generate
29
 
30
+ model, tokenizer = load("mlx-community/Qwen2.5-14B-Instruct-1M-abliterated-4bit")
31
 
32
  prompt="hello"
33