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
Copy file name to clipboardExpand all lines: README.md
+4-1Lines changed: 4 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -51,7 +51,9 @@ Learn more about tool calling <https://gorilla.cs.berkeley.edu/leaderboard.html>
51
51
├── DOCKER_VOICE_SETUP.md - Comprehensive guide for Docker voice functionality setup.
52
52
├── .dockerignore - This file contains the files and directories to be ignored by docker.
53
53
├── .devcontainer - This directory contains the devcontainer configuration files.
54
-
├── .env - This file contains the environment variables for the project. (Not included in the repository)
54
+
├── .env - This file contains the environment variables for the project. (Not included in the repository)
55
+
├── examples - An example implementation of how to use the inspect library
56
+
│ ├── examples/inspect_safety_demo.py - a demo of how to implement evaluations to the model to allow safety features.
55
57
├── INSPECT_SAFETY_GUIDE.md - Comprehensive guide for the Inspect AI safety layer integration.
56
58
├── IMPLEMENTATION_SUMMARY.md - Summary of the technical implementation and features of the project.
57
59
├── LICENSE - This file contains the license for the project.
@@ -89,6 +91,7 @@ Learn more about tool calling <https://gorilla.cs.berkeley.edu/leaderboard.html>
89
91
* Ollama for model serving and deployment. The original project can be found at [Ollama](https://ollama.com/)
90
92
* The project uses the Gradio library to create a user interface for the function calling LLM. The original project can be found at [Gradio](https://gradio.app/)
91
93
* The Text-to-Speech interface uses Edge TTS by Microsoft. The original project can be found at [Edge TTS](https://github.com/rany2/edge-tts). The voice chosen is Rehema which is a voice from Tanzania.
94
+
* The inspect library which provides an open source alternative for model evaluations by the UK AI Security Institute. More information can be found [here](https://github.com/UKGovernmentBEIS/inspect_ai)
0 commit comments