Update README.md
Browse files
README.md
CHANGED
@@ -29,6 +29,8 @@ So with regards to building a SillyTavern prompt template you basically want the
|
|
29 |
|
30 |
It doesn't give particularly verbose replies unless you're continueing a roleplay with verbose messages. Otherwise it's pretty bad.
|
31 |
|
|
|
|
|
32 |
[GGUFs care of Qaunt Cartel](https://huggingface.co/Quant-Cartel/Llama-3-8B-EGO-iMat-GGUF)
|
33 |
|
34 |
[exl2 rpcal care of Qaunt Cartel](https://huggingface.co/Quant-Cartel/Llama-3-8B-EGO-exl2-rpcal)
|
|
|
29 |
|
30 |
It doesn't give particularly verbose replies unless you're continueing a roleplay with verbose messages. Otherwise it's pretty bad.
|
31 |
|
32 |
+
Training was done using [qlora-pipe](https://github.com/tdrussell/qlora-pipe)
|
33 |
+
|
34 |
[GGUFs care of Qaunt Cartel](https://huggingface.co/Quant-Cartel/Llama-3-8B-EGO-iMat-GGUF)
|
35 |
|
36 |
[exl2 rpcal care of Qaunt Cartel](https://huggingface.co/Quant-Cartel/Llama-3-8B-EGO-exl2-rpcal)
|