munish0838
commited on
Commit
•
0b0fba3
1
Parent(s):
264bd61
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
pipeline_tag: text-generation
|
4 |
+
base_model: nakodanei/Blue-Orchid-2x7b
|
5 |
+
---
|
6 |
+
|
7 |
+
# QuantFactory/Blue-Orchid-2x7b-GGUF
|
8 |
+
This is quantized version of [nakodanei/Blue-Orchid-2x7b](https://huggingface.co/nakodanei/Blue-Orchid-2x7b) created using llama.cpp
|
9 |
+
|
10 |
+
# Model Description
|
11 |
+
|
12 |
+
Roleplaying focused MoE Mistral model.
|
13 |
+
|
14 |
+
One expert is a merge of mostly RP models, the other is a merge of mostly storywriting models. So it should be good at both. The base model is SanjiWatsuki/Kunoichi-DPO-v2-7B.
|
15 |
+
|
16 |
+
- Expert 1 is a merge of LimaRP, Limamono, Noromaid 0.4 DPO and good-robot.
|
17 |
+
- Expert 2 is a merge of Erebus, Holodeck, Dans-AdventurousWinds-Mk2, Opus, Ashhwriter and good-robot.
|
18 |
+
|
19 |
+
## Prompt template (LimaRP):
|
20 |
+
|
21 |
+
```
|
22 |
+
### Instruction:
|
23 |
+
{system prompt}
|
24 |
+
|
25 |
+
### Input:
|
26 |
+
User: {prompt}
|
27 |
+
|
28 |
+
### Response:
|
29 |
+
Character:
|
30 |
+
|
31 |
+
```
|
32 |
+
|
33 |
+
Alpaca prompt template should work fine too.
|