Update README.md
Browse files
README.md
CHANGED
@@ -111,13 +111,17 @@ model-index:
|
|
111 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fimbulvetr-Kuro-Lotus-10.7B
|
112 |
name: Open LLM Leaderboard
|
113 |
---
|
114 |
-
This model is a merge of my personal favourite models, i couldn't decide between them so why not have both? Without MOE cause gpu poor :3
|
115 |
|
116 |
-
|
117 |
|
118 |
-
|
|
|
119 |
|
120 |
-
|
|
|
|
|
|
|
|
|
121 |
|
122 |
|
123 |
# merge
|
|
|
111 |
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fimbulvetr-Kuro-Lotus-10.7B
|
112 |
name: Open LLM Leaderboard
|
113 |
---
|
|
|
114 |
|
115 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63df7c44f0c75dfb876272c0/knwDeWu0JVdH5EPB1knvh.png)
|
116 |
|
117 |
+
--------------------------------------------
|
118 |
+
* This model is a merge of my personal favourite models, i couldn't decide between them so why not have both? Without MOE cause gpu poor :3
|
119 |
|
120 |
+
* With my own tests it gives kuro-lotus like results without the requirement for a highly detailed character card and stays coherent when roping up to 8K context.
|
121 |
+
|
122 |
+
* I personally use the "Universal Light" preset in silly tavern, with "alpaca" the results can be short but are longer with "alpaca roleplay".
|
123 |
+
|
124 |
+
* "Universal Light" preset can be extremely creative but sometimes likes to act for user with some cards, for those i like just the "default" but any preset seems to work!
|
125 |
|
126 |
|
127 |
# merge
|