asadm commited on
Commit
060e781
·
unverified ·
1 Parent(s): b41f03a

talk-llama : move up-to-date demo to top (#1417)

Browse files
Files changed (1) hide show
  1. examples/talk-llama/README.md +4 -2
examples/talk-llama/README.md CHANGED
@@ -2,12 +2,14 @@
2
 
3
  Talk with an LLaMA AI in your terminal
4
 
5
- [Demo Talk](https://user-images.githubusercontent.com/1991296/228024237-848f998c-c334-46a6-bef8-3271590da83b.mp4)
6
-
7
  *Latest perf as of 2 Nov 2023 using Whisper Medium + LLaMA v2 13B Q8_0 on M2 Ultra:*
8
 
9
  https://github.com/ggerganov/whisper.cpp/assets/1991296/d97a3788-bf2a-4756-9a43-60c6b391649e
10
 
 
 
 
 
11
  ## Building
12
 
13
  The `talk-llama` tool depends on SDL2 library to capture audio from the microphone. You can build it like this:
 
2
 
3
  Talk with an LLaMA AI in your terminal
4
 
 
 
5
  *Latest perf as of 2 Nov 2023 using Whisper Medium + LLaMA v2 13B Q8_0 on M2 Ultra:*
6
 
7
  https://github.com/ggerganov/whisper.cpp/assets/1991296/d97a3788-bf2a-4756-9a43-60c6b391649e
8
 
9
+ *Previous demo running on CPUs*
10
+
11
+ [Demo Talk](https://user-images.githubusercontent.com/1991296/228024237-848f998c-c334-46a6-bef8-3271590da83b.mp4)
12
+
13
  ## Building
14
 
15
  The `talk-llama` tool depends on SDL2 library to capture audio from the microphone. You can build it like this: