Skip to content

Commit fcc0c93

Browse files
ggerganovvonstring
authored andcommitted
talk-llama : update to latest llama.cpp
1 parent cea5983 commit fcc0c93

File tree

6 files changed

+5748
-2048
lines changed

6 files changed

+5748
-2048
lines changed

examples/talk-llama/README.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ brew install sdl2
1919
make talk-llama
2020

2121
# Run it
22-
./talk-llama -mw ./models/ggml-small.en.bin -ml ../llama.cpp/models/13B/ggml-model-q4_0.bin -p "Georgi" -t 8
22+
./talk-llama -mw ./models/ggml-small.en.bin -ml ../llama.cpp/models/llama-13b/ggml-model-q4_0.gguf -p "Georgi" -t 8
2323
```
2424

2525
- The `-mw` argument specifies the Whisper model that you would like to use. Recommended `base` or `small` for real-time experience
@@ -36,7 +36,7 @@ This feature is especially helpful for maintaining context in long conversations
3636
Example usage:
3737

3838
```bash
39-
./talk-llama --session ./my-session-file -mw ./models/ggml-small.en.bin -ml ../llama.cpp/models/13B/ggml-model-q4_0.bin -p "Georgi" -t 8
39+
./talk-llama --session ./my-session-file -mw ./models/ggml-small.en.bin -ml ../llama.cpp/models/llama-13b/ggml-model-q4_0.gguf -p "Georgi" -t 8
4040
```
4141

4242
## TTS

0 commit comments

Comments
 (0)