Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,21 @@ language:
|
|
| 14 |
A roleplay-focused LoRA finetune of Mistral Nemo Instruct. Methodology and hyperparams inspired by [SorcererLM](https://huggingface.co/rAIfle/SorcererLM-8x22b-bf16) and [Slush](https://huggingface.co/crestf411/Q2.5-32B-Slush).
|
| 15 |
Renamed to Ink to distinguish from [insert every other rp tune ever], but it's the same data as was used in the [Teleut RP model](https://huggingface.co/allura-org/Teleut-7b-RP).
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
## Dataset
|
| 18 |
The worst mix of data you've ever seen. Like, seriously, you do not want to see the things that went into this model. It's bad.
|
| 19 |
|
|
|
|
| 14 |
A roleplay-focused LoRA finetune of Mistral Nemo Instruct. Methodology and hyperparams inspired by [SorcererLM](https://huggingface.co/rAIfle/SorcererLM-8x22b-bf16) and [Slush](https://huggingface.co/crestf411/Q2.5-32B-Slush).
|
| 15 |
Renamed to Ink to distinguish from [insert every other rp tune ever], but it's the same data as was used in the [Teleut RP model](https://huggingface.co/allura-org/Teleut-7b-RP).
|
| 16 |
|
| 17 |
+
## Testimonials
|
| 18 |
+
> dude Fizz, Ink is fucking **gas**
|
| 19 |
+
|
| 20 |
+
\- inflatebot
|
| 21 |
+
|
| 22 |
+
> First impression, I put this higher than Rocinante and Magnum Picaro
|
| 23 |
+
>
|
| 24 |
+
\- ShotMisser64
|
| 25 |
+
|
| 26 |
+
> I haven't tried any 12B models tbh, but I like the writing of this one
|
| 27 |
+
> Feels much better than most of Llama3-based models
|
| 28 |
+
>
|
| 29 |
+
\- Evoc
|
| 30 |
+
|
| 31 |
+
|
| 32 |
## Dataset
|
| 33 |
The worst mix of data you've ever seen. Like, seriously, you do not want to see the things that went into this model. It's bad.
|
| 34 |
|