hobaratio commited on
Commit
4e66e18
·
verified ·
1 Parent(s): 307b796

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +46 -0
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ language:
4
+ - en
5
+ base_model: FallenMerick/MN-Violet-Lotus-12B
6
+ library_name: transformers
7
+ tags:
8
+ - storywriting
9
+ - text adventure
10
+ - creative
11
+ - story
12
+ - writing
13
+ - fiction
14
+ - roleplaying
15
+ - rp
16
+ - mergekit
17
+ - merge
18
+ - mlx
19
+ - mlx-my-repo
20
+ ---
21
+
22
+ # hobaratio/MN-Violet-Lotus-12B-mlx-8Bit
23
+
24
+ The Model [hobaratio/MN-Violet-Lotus-12B-mlx-8Bit](https://huggingface.co/hobaratio/MN-Violet-Lotus-12B-mlx-8Bit) was converted to MLX format from [FallenMerick/MN-Violet-Lotus-12B](https://huggingface.co/FallenMerick/MN-Violet-Lotus-12B) using mlx-lm version **0.26.3**.
25
+
26
+ ## Use with mlx
27
+
28
+ ```bash
29
+ pip install mlx-lm
30
+ ```
31
+
32
+ ```python
33
+ from mlx_lm import load, generate
34
+
35
+ model, tokenizer = load("hobaratio/MN-Violet-Lotus-12B-mlx-8Bit")
36
+
37
+ prompt="hello"
38
+
39
+ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
40
+ messages = [{"role": "user", "content": prompt}]
41
+ prompt = tokenizer.apply_chat_template(
42
+ messages, tokenize=False, add_generation_prompt=True
43
+ )
44
+
45
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
46
+ ```