Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,7 @@ This model is still uploading. README will be here shortly.
|
|
| 2 |
|
| 3 |
If you're too impatient to wait for that (of course you are), to run these files you need:
|
| 4 |
1. llama.cpp as of [this commit or later](https://github.com/ggerganov/llama.cpp/commit/e76d630df17e235e6b9ef416c45996765d2e36fb)
|
|
|
|
| 5 |
2. To add new command line parameter `-gqa 8`
|
| 6 |
|
| 7 |
Example command:
|
|
|
|
| 2 |
|
| 3 |
If you're too impatient to wait for that (of course you are), to run these files you need:
|
| 4 |
1. llama.cpp as of [this commit or later](https://github.com/ggerganov/llama.cpp/commit/e76d630df17e235e6b9ef416c45996765d2e36fb)
|
| 5 |
+
- For users who don't want to compile from source, you can use the binaries from [release master-3602ac4](https://github.com/ggerganov/llama.cpp/releases/tag/master-3602ac4)
|
| 6 |
2. To add new command line parameter `-gqa 8`
|
| 7 |
|
| 8 |
Example command:
|