Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,11 @@ tags:
|
|
| 15 |
|
| 16 |
This is really a followup and improvement off my original Lumi-Tess model.
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
# model
|
| 19 |
A large context (128K) uncencored Llama 3 instruct model focussed on story & RP.
|
| 20 |
I found the Smaug version of lama very impressive, exept for a couple of quirks and the default context window.
|
|
|
|
| 15 |
|
| 16 |
This is really a followup and improvement off my original Lumi-Tess model.
|
| 17 |
|
| 18 |
+
I have noticed that the quant versions have a very poor context windows.
|
| 19 |
+
So i made a newer version with gradent in stead of giraffe so the context window will hopefully remain
|
| 20 |
+
much better with lower quant sizes.
|
| 21 |
+
https://huggingface.co/ryzen88/Llama-3-70b-Arimas-story-RP-V1.5
|
| 22 |
+
|
| 23 |
# model
|
| 24 |
A large context (128K) uncencored Llama 3 instruct model focussed on story & RP.
|
| 25 |
I found the Smaug version of lama very impressive, exept for a couple of quirks and the default context window.
|