From d6fb16e05524eb99a28436e73d7f45b1ca6f8b6d Mon Sep 17 00:00:00 2001 From: Andrei Betlen Date: Thu, 25 Jan 2024 10:51:48 -0500 Subject: [PATCH] docs: Update README --- README.md | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index f602b17..7813c96 100644 --- a/README.md +++ b/README.md @@ -163,7 +163,7 @@ Below is a short example demonstrating how to use the high-level API to for basi ) >>> output = llm( "Q: Name the planets in the solar system? A: ", # Prompt - max_tokens=32, # Generate up to 32 tokens + max_tokens=32, # Generate up to 32 tokens, set to None to generate up to the end of the context window stop=["Q:", "\n"], # Stop generating just before the model would generate a new question echo=True # Echo the prompt back in the output ) # Generate a completion, can also call create_completion @@ -425,6 +425,9 @@ pip install -e .[all] make clean ``` +You can also test out specific commits of `lama.cpp` by checking out the desired commit in the `vendor/llama.cpp` submodule and then running `make clean` and `pip install -e .` again. Any changes in the `llama.h` API will require +changes to the `llama_cpp/llama_cpp.py` file to match the new API (additional changes may be required elsewhere). + ## FAQ ### Are there pre-built binaries / binary wheels available?