Update README.md
Browse files
README.md
CHANGED
@@ -6,15 +6,15 @@ tags:
|
|
6 |
|
7 |
# LLAMA-GGML-v2
|
8 |
|
9 |
-
This is
|
10 |
|
11 |
-
|
12 |
-
|
13 |
-
## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 12th 2023 - commit b9fd7ee)!
|
14 |
|
15 |
llama.cpp recently made a breaking change to its quantisation methods.
|
16 |
|
17 |
-
I have quantised the GGML files in this repo with the latest version.
|
|
|
|
|
18 |
|
19 |
## How to run in `text-generation-webui`
|
20 |
|
|
|
6 |
|
7 |
# LLAMA-GGML-v2
|
8 |
|
9 |
+
This is repo for LLaMA models quantised down to 4bit for the latest [llama.cpp](https://github.com/ggerganov/llama.cpp) GGML v2 format.
|
10 |
|
11 |
+
## THE FILES REQUIRES LATEST LLAMA.CPP (May 12th 2023 - commit b9fd7ee)!
|
|
|
|
|
12 |
|
13 |
llama.cpp recently made a breaking change to its quantisation methods.
|
14 |
|
15 |
+
I have quantised the GGML files in this repo with the latest version.
|
16 |
+
|
17 |
+
Therefore you will require llama.cpp compiled on May 12th or later (commit `b9fd7ee` or later) to use them.
|
18 |
|
19 |
## How to run in `text-generation-webui`
|
20 |
|