From 554b54152145c30618bac171efb712cf4a7d1e96 Mon Sep 17 00:00:00 2001
From: Pavol Rusnak <pavol@rusnak.io>
Date: Sat, 18 Mar 2023 21:58:46 +0100
Subject: [PATCH 1/4] Add memory/disk requirements to readme

---
 README.md | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 808d54e89..fc8b2fda3 100644
--- a/README.md
+++ b/README.md
@@ -155,7 +155,17 @@ python3 convert-pth-to-ggml.py models/7B/ 1
 
 When running the larger models, make sure you have enough disk space to store all the intermediate files.
 
-TODO: add model disk/mem requirements
+### Memory/Disk Requirements
+
+As the models are currently fully loaded into memory, you will need adequate disk space to save them
+and sufficient RAM to load them. At the moment, memory and disk requirements are the same.
+
+| model | original size | quantized size (4-bit) |
+|-------|---------------|------------------------|
+| 7B    | 13 GB         | 3.9 GB                 |
+| 15B   | 24 GB         | 7.8 GB                 |
+| 30B   | 60 GB         | 19.5 GB                |
+| 65B   | 120 GB        | 38.5 GB                |
 
 ### Interactive mode
 

From 1e5a6d088d0f3a967c6e86298a756daec9e8df12 Mon Sep 17 00:00:00 2001
From: Pavol Rusnak <pavol@rusnak.io>
Date: Sat, 18 Mar 2023 22:20:04 +0100
Subject: [PATCH 2/4] Add note about Python 3.11 to readme

---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index fc8b2fda3..187f82f61 100644
--- a/README.md
+++ b/README.md
@@ -153,6 +153,8 @@ python3 convert-pth-to-ggml.py models/7B/ 1
 ./main -m ./models/7B/ggml-model-q4_0.bin -n 128
 ```
 
+Currently, it's best to use Python 3.9 or Python 3.10, as `sentencepiece` has not yet published a wheel for Python 3.11.
+
 When running the larger models, make sure you have enough disk space to store all the intermediate files.
 
 ### Memory/Disk Requirements

From 6f61c18ec9a30416e21ed5abfb1321bdb14979be Mon Sep 17 00:00:00 2001
From: Pavol Rusnak <pavol@rusnak.io>
Date: Sat, 18 Mar 2023 22:39:46 +0100
Subject: [PATCH 3/4] Fix typo in readme

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 187f82f61..1fe5b5426 100644
--- a/README.md
+++ b/README.md
@@ -165,7 +165,7 @@ and sufficient RAM to load them. At the moment, memory and disk requirements are
 | model | original size | quantized size (4-bit) |
 |-------|---------------|------------------------|
 | 7B    | 13 GB         | 3.9 GB                 |
-| 15B   | 24 GB         | 7.8 GB                 |
+| 13B   | 24 GB         | 7.8 GB                 |
 | 30B   | 60 GB         | 19.5 GB                |
 | 65B   | 120 GB        | 38.5 GB                |
 

From d7def1a7524f712e5ebb7cd02bab0f13aa56a7f9 Mon Sep 17 00:00:00 2001
From: Ronsor <ronsor@ronsor.pw>
Date: Sat, 18 Mar 2023 17:10:47 -0700
Subject: [PATCH 4/4] Warn user if a context size greater than 2048 tokens is
 specified (#274)

LLaMA doesn't support more than 2048 token context sizes, and going above that produces terrible results.
---
 main.cpp | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/main.cpp b/main.cpp
index c88405b82..105dd91ee 100644
--- a/main.cpp
+++ b/main.cpp
@@ -792,6 +792,11 @@ int main(int argc, char ** argv) {
     if (gpt_params_parse(argc, argv, params) == false) {
         return 1;
     }
+    
+    if (params.n_ctx > 2048) {
+        fprintf(stderr, "%s: warning: model does not support context sizes greater than 2048 tokens (%d specified);"
+                "expect poor results\n", __func__, params.n_ctx);
+    }
 
     if (params.seed < 0) {
         params.seed = time(NULL);