Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,13 @@
|
|
| 2 |
|
| 3 |
_NOTE: model card is WIP_
|
| 4 |
|
| 5 |
-
GPT2-L (774M parameters) trained on the Wizard of Wikipedia dataset for 40k steps with 34/36 layers frozen using `aitextgen`. Designed for use with [ai-msgbot](https://github.com/pszemraj/ai-msgbot).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
_NOTE: model card is WIP_
|
| 4 |
|
| 5 |
+
GPT2-L (774M parameters) trained on the Wizard of Wikipedia dataset for 40k steps with 34/36 layers frozen using `aitextgen`. Designed for use with [ai-msgbot](https://github.com/pszemraj/ai-msgbot).
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
## conversation data
|
| 9 |
+
|
| 10 |
+
The dataset was tokenized and fed to the model as a conversation between two speakers, whose names are below. this is relevant for writing prompts and filtering/extracting text from responses.
|
| 11 |
+
|
| 12 |
+
`script_speaker_name` = `person alpha`
|
| 13 |
+
|
| 14 |
+
`script_responder_name` = `person beta`
|