Update README.md
Browse files
README.md
CHANGED
|
@@ -49,6 +49,12 @@ It uses Cosmopolitan Libc to turn LLM weights into runnable llama.cpp
|
|
| 49 |
binaries that run on the stock installs of six OSes for both ARM64 and
|
| 50 |
AMD64.
|
| 51 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
## About Quantization Formats (General Advice)
|
| 53 |
|
| 54 |
Your choice of quantization format depends on three things:
|
|
|
|
| 49 |
binaries that run on the stock installs of six OSes for both ARM64 and
|
| 50 |
AMD64.
|
| 51 |
|
| 52 |
+
In addition to being executables, llamafiles are also zip archives. Each
|
| 53 |
+
llamafile contains a GGUF file, which you can extract using the `unzip`
|
| 54 |
+
command. If you want to change or add files to your llamafiles, then the
|
| 55 |
+
`zipalign` command (distributed on the llamafile github) should be used
|
| 56 |
+
instead of the traditional `zip` command.
|
| 57 |
+
|
| 58 |
## About Quantization Formats (General Advice)
|
| 59 |
|
| 60 |
Your choice of quantization format depends on three things:
|