athirdpath
commited on
Commit
•
f2a9b1d
1
Parent(s):
958aece
Update README.md
Browse files
README.md
CHANGED
@@ -5,12 +5,12 @@ language:
|
|
5 |
tags:
|
6 |
- not-for-all-audiences
|
7 |
---
|
8 |
-
<p align="center"><img src="https://i.ibb.co/pbpJHpk/iambe-sml.png"/><font size="6"> <b>Iambe-
|
9 |
<p align="center"><font size="4"> <b>Alpaca prompt formatting</b> </font></p>
|
10 |
|
11 |
### Description
|
12 |
|
13 |
-
Named after a charming daughter of Echo and Pan in Greek myth, Iambe-
|
14 |
|
15 |
Iambe is intended to have the best realistically possible understanding of instructions, anatomy and scene state for a 20b merge, while remaining passionate and humanoid in "voice".
|
16 |
|
@@ -18,6 +18,9 @@ Iambe is intended to have the best realistically possible understanding of instr
|
|
18 |
|
19 |
Take a look at [the dataset v2 Iambe and I created together](https://huggingface.co/datasets/athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW) for more info. The cDPO training was done directly on Iambe-20b-DARE-v2, I was researching 11b merges to reduce the compute, but it went nowhere, so I just bit the bullet on cost. The notebook used to train this model is also available in the dataset's repo.
|
20 |
|
|
|
|
|
|
|
21 |
<p align="center"><font size="5"> <b>4-bit Assistant Example</b> </font></p>
|
22 |
<p align="center"><img src="https://i.postimg.cc/HxNsPRSk/Screenshot-2023-12-06-214901.png"/>
|
23 |
|
|
|
5 |
tags:
|
6 |
- not-for-all-audiences
|
7 |
---
|
8 |
+
<p align="center"><img src="https://i.ibb.co/pbpJHpk/iambe-sml.png"/><font size="6"> <b>Iambe-RP-cDPO-20b</b> </font></p>
|
9 |
<p align="center"><font size="4"> <b>Alpaca prompt formatting</b> </font></p>
|
10 |
|
11 |
### Description
|
12 |
|
13 |
+
Named after a charming daughter of Echo and Pan in Greek myth, Iambe-RP is, as far as I am aware, the very first LLM trained with DPO on an erotic roleplay dataset.
|
14 |
|
15 |
Iambe is intended to have the best realistically possible understanding of instructions, anatomy and scene state for a 20b merge, while remaining passionate and humanoid in "voice".
|
16 |
|
|
|
18 |
|
19 |
Take a look at [the dataset v2 Iambe and I created together](https://huggingface.co/datasets/athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW) for more info. The cDPO training was done directly on Iambe-20b-DARE-v2, I was researching 11b merges to reduce the compute, but it went nowhere, so I just bit the bullet on cost. The notebook used to train this model is also available in the dataset's repo.
|
20 |
|
21 |
+
<p align="center"><font size="5"> <b>Roleplay Example @ q5_k_m</b> </font></p>
|
22 |
+
<p align="center"><img src="https://i.ibb.co/hFz5mdF/Screenshot-2023-12-07-005350.png"/>
|
23 |
+
|
24 |
<p align="center"><font size="5"> <b>4-bit Assistant Example</b> </font></p>
|
25 |
<p align="center"><img src="https://i.postimg.cc/HxNsPRSk/Screenshot-2023-12-06-214901.png"/>
|
26 |
|