You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
4. **Give Terminal app the required permissions**: As a last step, the Terminal app will ask for permission for "Screen Recording" and "Accessibility" in the "Security & Privacy" page of Mac's "System Preferences".
We use [PDM](https://pdm-project.org/latest/) as our package and dependency manager. You can find instructions for insallation and usage [here](https://pdm-project.org/latest/#recommended-installation-method).
85
89
86
90
## Using `operate` Modes
87
91
@@ -91,7 +95,7 @@ An additional model is now compatible with the Self Operating Computer Framework
91
95
92
96
Start `operate` with the Gemini model
93
97
94
-
```
98
+
```bash
95
99
operate -m gemini-pro-vision
96
100
```
97
101
@@ -115,7 +119,7 @@ For this initial version, a simple YOLOv8 model is trained for button detection,
115
119
116
120
Start `operate` with the SoM model
117
121
118
-
```
122
+
```bash
119
123
operate -m gpt-4-with-som
120
124
```
121
125
@@ -124,38 +128,38 @@ operate -m gpt-4-with-som
124
128
The framework supports voice inputs for the objective. Try voice by following the instructions below.
125
129
**Clone the repo** to a directory on your computer:
0 commit comments