Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,15 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- 4-bit
|
| 5 |
- AWQ
|
| 6 |
- text-generation
|
|
@@ -10,6 +19,15 @@ pipeline_tag: text-generation
|
|
| 10 |
inference: false
|
| 11 |
quantized_by: Suparious
|
| 12 |
---
|
| 13 |
-
#
|
| 14 |
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
base_model:
|
| 4 |
+
- Alsebay/NarumashiRTS-V2
|
| 5 |
+
- SanjiWatsuki/Kunoichi-DPO-v2-7B
|
| 6 |
+
- Nitral-AI/KukulStanta-7B
|
| 7 |
library_name: transformers
|
| 8 |
tags:
|
| 9 |
+
- moe
|
| 10 |
+
- merge
|
| 11 |
+
- roleplay
|
| 12 |
+
- Roleplay
|
| 13 |
- 4-bit
|
| 14 |
- AWQ
|
| 15 |
- text-generation
|
|
|
|
| 19 |
inference: false
|
| 20 |
quantized_by: Suparious
|
| 21 |
---
|
| 22 |
+
# Alsebay/NaruMOE-3x7B-v2 AWQ
|
| 23 |
|
| 24 |
+
- Model creator: [Alsebay](https://huggingface.co/Alsebay)
|
| 25 |
+
- Original model: [NaruMOE-3x7B-v2](https://huggingface.co/Alsebay/NaruMOE-3x7B-v2)
|
| 26 |
+
|
| 27 |
+
## Model Summary
|
| 28 |
+
|
| 29 |
+
A MoE model for Roleplaying. Since 7B model is small enough, we can combine them to a bigger model (Which CAN be smarter).
|
| 30 |
+
|
| 31 |
+
Adapte (some limited) TSF (Trans Sexual Fiction) content because I have include my pre-train model in.
|
| 32 |
+
|
| 33 |
+
Worse than V1 in logic, but better in expression.
|