From 8bb940416869a821d4e320ef3dd2b8b11024f083 Mon Sep 17 00:00:00 2001
From: Mikko Juola <mikjuo@gmail.com>
Date: Sat, 11 Mar 2023 00:47:32 -0800
Subject: [PATCH] Update README to clarify this is a Rust project and to show
 how to change temperature, top_k, top_p stuff.

---
 README.md | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 768401e..06134fa 100644
--- a/README.md
+++ b/README.md
@@ -16,7 +16,9 @@ Well sort of, it doesn't unzip them automatically (see below).
 
 # How to run
 
-You will need the LLaMA-7B weights first. Refer to https://github.com/facebookresearch/llama/
+You will need Rust. Make sure you can run `cargo` from a command line.
+
+You will need to download LLaMA-7B weights. Refer to https://github.com/facebookresearch/llama/
 
 Once you have 7B weights, and the `tokenizer.model` it comes with, you need to
 decompress it.
@@ -36,6 +38,9 @@ cargo run --release -- --tokenizer-model /path/to/tokenizer.model --model-path /
 Right now it seems to use around ~25 gigabytes of memory. Internally all
 weights are cast to 32-bit floats.
 
+You can use `--temperature`, `--top-p` and `--top-k` to adjust token sampler
+settings.
+
 # Future plans
 
 This is a hobby thing for me so don't expect updates or help.