llama.cpp/examples/simple-chat
2024-11-01 16:53:35 +01:00
..
CMakeLists.txt llama : add simple-chat example 2024-11-01 16:53:35 +01:00
README.md llama : add simple-chat example 2024-11-01 16:53:35 +01:00
simple-chat.cpp llama : add simple-chat example 2024-11-01 16:53:35 +01:00

llama.cpp/example/simple-chat

The purpose of this example is to demonstrate a minimal usage of llama.cpp to create a simple chat program using the built-in chat template in GGUF files.

./llama-simple-chat -m ./models/llama-7b-v2/ggml-model-f16.gguf -c 2048
...