Update README.md
Browse files
README.md
CHANGED
@@ -17,7 +17,7 @@ Image to be replaced :P
|
|
17 |
|
18 |
This model uses the Alpaca **prompting format**. Unlike the base model this one is tuned on **16384 sequence length**. This was due to memory constraints.
|
19 |
|
20 |
-
|
21 |
|
22 |
Miqu PlayMaid 70B a roleplay focused finetune using MiquMaid v2 70B DPO by [Undi95](https://huggingface.co/Undi95) and [IkariDev](https://huggingface.co/IkariDev) as base.
|
23 |
|
|
|
17 |
|
18 |
This model uses the Alpaca **prompting format**. Unlike the base model this one is tuned on **16384 sequence length**. This was due to memory constraints.
|
19 |
|
20 |
+
Like Undi and Ikari, I followed my finetune up by making a MoE, made of Miqu PlayMaid 70B and Miqu 70B DPO.
|
21 |
|
22 |
Miqu PlayMaid 70B a roleplay focused finetune using MiquMaid v2 70B DPO by [Undi95](https://huggingface.co/Undi95) and [IkariDev](https://huggingface.co/IkariDev) as base.
|
23 |
|