richardyoung commited on
Commit
53b7cce
·
verified ·
1 Parent(s): 9a9c5c5

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +13 -1
README.md CHANGED
@@ -31,7 +31,19 @@ These binaries are derived from the upstream [`Kwaipilot/KAT-Dev-72B-Exp`](https
31
 
32
  ## Usage with Ollama
33
 
34
- Example for the `iq4_xs` quantization:
 
 
 
 
 
 
 
 
 
 
 
 
35
 
36
  ```bash
37
  ollama create kat-dev-72b-iq4_xs -f modelfiles/kat-dev-72b--iq4_xs.Modelfile
 
31
 
32
  ## Usage with Ollama
33
 
34
+ ### Quick Start (Pull from Registry)
35
+
36
+ You can directly pull and run the model from the Ollama registry:
37
+
38
+ ```bash
39
+ ollama run richardyoung/kat-dev-72b:iq3_m
40
+ ```
41
+
42
+ Available tags: `iq2_m`, `iq2_xxs`, `iq3_m`, `iq4_xs`
43
+
44
+ ### Alternative: Build from Modelfile
45
+
46
+ You can also create the model locally from the included Modelfiles:
47
 
48
  ```bash
49
  ollama create kat-dev-72b-iq4_xs -f modelfiles/kat-dev-72b--iq4_xs.Modelfile