aimeri commited on
Commit
b8042ce
·
verified ·
1 Parent(s): adeb2b3

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +37 -0
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: aimeri/PersonalityWindDolphin-24B
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ - PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
8
+ - PocketDoc/Dans-DangerousWinds-V1.1.1-24b
9
+ - mlx
10
+ - mlx-my-repo
11
+ ---
12
+
13
+ # aimeri/PersonalityWindDolphin-24B-mlx-6Bit
14
+
15
+ The Model [aimeri/PersonalityWindDolphin-24B-mlx-6Bit](https://huggingface.co/aimeri/PersonalityWindDolphin-24B-mlx-6Bit) was converted to MLX format from [aimeri/PersonalityWindDolphin-24B](https://huggingface.co/aimeri/PersonalityWindDolphin-24B) using mlx-lm version **0.26.4**.
16
+
17
+ ## Use with mlx
18
+
19
+ ```bash
20
+ pip install mlx-lm
21
+ ```
22
+
23
+ ```python
24
+ from mlx_lm import load, generate
25
+
26
+ model, tokenizer = load("aimeri/PersonalityWindDolphin-24B-mlx-6Bit")
27
+
28
+ prompt="hello"
29
+
30
+ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
31
+ messages = [{"role": "user", "content": prompt}]
32
+ prompt = tokenizer.apply_chat_template(
33
+ messages, tokenize=False, add_generation_prompt=True
34
+ )
35
+
36
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
37
+ ```