extending context window

Author: antimatter15

README.md

@@ -61,6 +61,11 @@ TODO
 
 Torrent: `magnet:?xt=urn:btih:053b3d54d2e77ff020ebddf51dad681f2a651071&dn=ggml-alpaca-13b-q4.bin&tr=udp%3A%2F%2Ftracker.opentrackr.org%3A1337%2Fannounce&tr=udp%3A%2F%2Fopentracker.i2p.rocks%3A6969%2Fannounce&tr=udp%3A%2F%2Ftracker.openbittorrent.com%3A6969%2Fannounce&tr=udp%3A%2F%2F9.rarbg.com%3A2810%2Fannounce`
 
+
+```
+./chat -m ggml-alpaca-13b-q4.bin
+```
+
 ## Credit
 
 This combines [Facebook's LLaMA](https://github.com/facebookresearch/llama), [Stanford Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html), [alpaca-lora](https://github.com/tloen/alpaca-lora) and [corresponding weights](https://huggingface.co/tloen/alpaca-lora-7b/tree/main) by Eric Wang (which uses [Jason Phang's implementation of LLaMA](https://github.com/huggingface/transformers/pull/21955) on top of Hugging Face Transformers), and [llama.cpp](https://github.com/ggerganov/llama.cpp) by Georgi Gerganov. The chat implementation is based on Matvey Soloviev's [Interactive Mode](https://github.com/ggerganov/llama.cpp/pull/61) for llama.cpp. Inspired by [Simon Willison's](https://til.simonwillison.net/llms/llama-7b-m2) getting started guide for LLaMA.

chat.cpp

@@ -798,6 +798,7 @@ int main(int argc, char ** argv) {
 
     params.temp = 0.1f;
     params.top_p = 0.95f;
+    params.n_ctx = 2048;
     params.interactive = true;
     params.interactive_start = true;
     params.use_color = true;