Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,34 @@
|
|
1 |
---
|
2 |
license: cc-by-sa-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: cc-by-sa-4.0
|
3 |
+
datasets:
|
4 |
+
- maywell/ko_wikidata_QA
|
5 |
+
- kyujinpy/OpenOrca-KO
|
6 |
+
- Anthropic/hh-rlhf
|
7 |
+
language:
|
8 |
+
- en
|
9 |
+
- ko
|
10 |
+
pipeline_tag: text-generation
|
11 |
---
|
12 |
+
|
13 |
+
# PiVoT-0.1-early
|
14 |
+
|
15 |
+
![image/png](./PiVoT.png)
|
16 |
+
|
17 |
+
# **Model Details**
|
18 |
+
|
19 |
+
### Description
|
20 |
+
PivoT is Finetuned model based on Mistral 7B. It is variation from Synatra v0.3 RP which has shown decent performance.
|
21 |
+
|
22 |
+
PiVoT-0.1-Evil-**a** is an **Evil tuned** Version of PiVoT. It finetuned by method below.
|
23 |
+
|
24 |
+
PiVot-0.1-Evil-**b** has Noisy Embedding tuned. It would have more variety in results.
|
25 |
+
|
26 |
+
![image/png](./eviltune.png)
|
27 |
+
|
28 |
+
OpenOrca Dataset used when finetune PiVoT variation. Arcalive Ai Chat Chan log 7k, [ko_wikidata_QA](https://huggingface.co/datasets/maywell/ko_wikidata_QA), [kyujinpy/OpenOrca-KO](https://huggingface.co/datasets/kyujinpy/OpenOrca-KO) and other datasets used on base model.
|
29 |
+
|
30 |
+
Follow me on twitter: https://twitter.com/stablefluffy
|
31 |
+
|
32 |
+
Consider Support me making these model alone: https://www.buymeacoffee.com/mwell or with Runpod Credit Gift 💕
|
33 |
+
|
34 |
+
Contact me on Telegram: https://t.me/AlzarTakkarsen
|