Update README.md
Browse files
README.md
CHANGED
@@ -31,4 +31,4 @@ llama-cli --model <model name>.gguf --control-vector-scaled <model name>-dark.gg
|
|
31 |
- Some models like `command-r:35b` and `command-r-plus:104b` need lower scale factors, whereas `miqu-1:70b` seems to need (much) higher scale factors to stamp out pesky redemption arcs.
|
32 |
- You can use one control vector file alone if you want, or alternatively set the scale factor to `0.0` for traits you don't want to use.
|
33 |
- You can use the same "`--control-vector-scaled`" command line arguments for "`llama-server`" as in the above "`llama-cli`" examples.
|
34 |
-
- Make sure you have a version of `llama.cpp` from after `27/06/24` - the [PR to use multiple control vectors together](https://github.com/ggerganov/llama.cpp/commit/97877eb10bd8e7f8023420b5b5300bcbdadd62dc) was only added on that date.
|
|
|
31 |
- Some models like `command-r:35b` and `command-r-plus:104b` need lower scale factors, whereas `miqu-1:70b` seems to need (much) higher scale factors to stamp out pesky redemption arcs.
|
32 |
- You can use one control vector file alone if you want, or alternatively set the scale factor to `0.0` for traits you don't want to use.
|
33 |
- You can use the same "`--control-vector-scaled`" command line arguments for "`llama-server`" as in the above "`llama-cli`" examples.
|
34 |
+
- Make sure you have a version of `llama.cpp` from after `27/06/24` - the [PR to use multiple control vectors together](https://github.com/ggerganov/llama.cpp/commit/97877eb10bd8e7f8023420b5b5300bcbdadd62dc) was only added on that date. Older versions of `llama.cpp` will just silently load the first control vector (and none of the others) if the layer index of the final direction in each file does not match!!!
|