codingmavin commited on
Commit
2f61e32
·
verified ·
1 Parent(s): 31a8f1f

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +33 -0
README.md ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: skumar9/Llama-medx_v3.2
5
+ tags:
6
+ - mlx
7
+ ---
8
+
9
+ # codingmavin/Llama-medx_v3.2-mlx-8Bit
10
+
11
+ The Model [codingmavin/Llama-medx_v3.2-mlx-8Bit](https://huggingface.co/codingmavin/Llama-medx_v3.2-mlx-8Bit) was converted to MLX format from [skumar9/Llama-medx_v3.2](https://huggingface.co/skumar9/Llama-medx_v3.2) using mlx-lm version **0.22.1**.
12
+
13
+ ## Use with mlx
14
+
15
+ ```bash
16
+ pip install mlx-lm
17
+ ```
18
+
19
+ ```python
20
+ from mlx_lm import load, generate
21
+
22
+ model, tokenizer = load("codingmavin/Llama-medx_v3.2-mlx-8Bit")
23
+
24
+ prompt="hello"
25
+
26
+ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
27
+ messages = [{"role": "user", "content": prompt}]
28
+ prompt = tokenizer.apply_chat_template(
29
+ messages, tokenize=False, add_generation_prompt=True
30
+ )
31
+
32
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
33
+ ```