Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ This is a double fine-tuned version of Mistral Small 24B Base 2501.
|
|
| 12 |
|
| 13 |
Stage 1 was shoving 30M tokens of human-writen story content into it using completion training ([ToastyPigeon/ms3-base-roselily](https://huggingface.co/ToastyPigeon/ms3-base-roselily)), which is about half of my WIP Roselily dataset (~60M tokens total).
|
| 14 |
|
| 15 |
-
Stage 2 was teaching it instruct (this model).
|
| 16 |
|
| 17 |
This model should accept (in theory) any of the following instruct formats:
|
| 18 |
|
|
|
|
| 12 |
|
| 13 |
Stage 1 was shoving 30M tokens of human-writen story content into it using completion training ([ToastyPigeon/ms3-base-roselily](https://huggingface.co/ToastyPigeon/ms3-base-roselily)), which is about half of my WIP Roselily dataset (~60M tokens total).
|
| 14 |
|
| 15 |
+
Stage 2 was teaching it instruct (this model) using a mix of public instruction following data and a private instruct dataset from ZeusLabs.
|
| 16 |
|
| 17 |
This model should accept (in theory) any of the following instruct formats:
|
| 18 |
|