Update README.md
Browse files
README.md
CHANGED
|
@@ -10,23 +10,23 @@ tags:
|
|
| 10 |
- merge
|
| 11 |
|
| 12 |
---
|
| 13 |
-
# NemoDori-v0.
|
| 14 |
|
| 15 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 16 |
|
| 17 |
-
The second child from [NemoDori-v0.2-12B-MN-BT](https://huggingface.co/RozGrov/NemoDori-v0.2-12B-MN-BT), a sibling to [**v0.
|
| 18 |
|
| 19 |
**The purpose** is to find a way to increase v0.2 capability to stay **aware of the past conversations** and **follow instructions better**, especially the last one (depth-0),
|
| 20 |
while keeping it's **creativity and capability to (E)RP**.
|
| 21 |
This model is one of the few childs to try to fulfill that.
|
| 22 |
|
| 23 |
-
In my short testing so far, I think it's **slightly more aware of what's in the past and what it's instructed to do**, but the **response format is not very consistent
|
| 24 |
<br>
|
| 25 |
You can go up until temp 2 with this boy (just like it predecessor [v0.1](https://huggingface.co/RozGrov/NemoDori-v0.1-12B-MS)), but it **will not** satisfy you, because it'll spew out some old english in a modern way kind of thing.
|
| 26 |
<br>
|
| 27 |
Anyway, tweak the preset all you want in ST (the harmless ones), it will still able to respond correctly. Use preset in [v0.1](https://huggingface.co/RozGrov/NemoDori-v0.1-12B-MS) if not.
|
| 28 |
|
| 29 |
-
You may give me feedback on how I can fulfill my-*ahem* it's purpose while keeping it as low as not-70B.
|
| 30 |
<br>
|
| 31 |
Fine-tune is... pretty expensive for me, and I'm not ready for that (yet, tho i'm interested).
|
| 32 |
|
|
|
|
| 10 |
- merge
|
| 11 |
|
| 12 |
---
|
| 13 |
+
# NemoDori-v0.2.2-12B-MN-ties
|
| 14 |
|
| 15 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 16 |
|
| 17 |
+
The second child from [NemoDori-v0.2-12B-MN-BT](https://huggingface.co/RozGrov/NemoDori-v0.2-12B-MN-BT), a sibling to [**v0.2.1**](https://huggingface.co/RozGrov/NemoDori-v0.2.1-12B-MN-BT).
|
| 18 |
|
| 19 |
**The purpose** is to find a way to increase v0.2 capability to stay **aware of the past conversations** and **follow instructions better**, especially the last one (depth-0),
|
| 20 |
while keeping it's **creativity and capability to (E)RP**.
|
| 21 |
This model is one of the few childs to try to fulfill that.
|
| 22 |
|
| 23 |
+
In my short testing so far, I think it's **slightly more aware of what's in the past and what it's instructed to do**, but the **response format is not very consistent**. Though, this might be because of my testing temp or bad instructions.
|
| 24 |
<br>
|
| 25 |
You can go up until temp 2 with this boy (just like it predecessor [v0.1](https://huggingface.co/RozGrov/NemoDori-v0.1-12B-MS)), but it **will not** satisfy you, because it'll spew out some old english in a modern way kind of thing.
|
| 26 |
<br>
|
| 27 |
Anyway, tweak the preset all you want in ST (the harmless ones), it will still able to respond correctly. Use preset in [v0.1](https://huggingface.co/RozGrov/NemoDori-v0.1-12B-MS) if not.
|
| 28 |
|
| 29 |
+
You may give me feedback on anything, or guide me how I can fulfill my-*ahem* it's purpose while keeping it as low as not-70B.
|
| 30 |
<br>
|
| 31 |
Fine-tune is... pretty expensive for me, and I'm not ready for that (yet, tho i'm interested).
|
| 32 |
|