Update README.md
Browse files
README.md
CHANGED
@@ -4,7 +4,7 @@ license: llama2
|
|
4 |
# Augmental-13b -- Human-written, AI-enhanced
|
5 |
|
6 |
## Details at a glance
|
7 |
-
- What it is: MythoMax 13b finetuned on a new high-quality augmented (read: human-written, AI-enhanced) RP dataset with
|
8 |
- Prompt format: SillyTavern.
|
9 |
- What sets it apart: The "augmented data" approach that MythoMakise took has been generalized beyond one character, refined to be cheaper, improved to have more diversity of writing, and scaled up by a factor of 8. Importantly, an additional GPT-4 pass was done on the dataset, where it chose specific lines to turn into much longer and more descriptive ones. As a result, this model excels at longer responses.
|
10 |
- Model quality as per my own ad-hoc testing: really good
|
|
|
4 |
# Augmental-13b -- Human-written, AI-enhanced
|
5 |
|
6 |
## Details at a glance
|
7 |
+
- What it is: MythoMax 13b finetuned on a new high-quality augmented (read: human-written, AI-enhanced) RP dataset with 7.85k+ examples. Trained on multiple different characters with a wide range of personalities (from Tsunderes to catgirls).
|
8 |
- Prompt format: SillyTavern.
|
9 |
- What sets it apart: The "augmented data" approach that MythoMakise took has been generalized beyond one character, refined to be cheaper, improved to have more diversity of writing, and scaled up by a factor of 8. Importantly, an additional GPT-4 pass was done on the dataset, where it chose specific lines to turn into much longer and more descriptive ones. As a result, this model excels at longer responses.
|
10 |
- Model quality as per my own ad-hoc testing: really good
|