Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,8 @@ Trained on [mistral-7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a b
|
|
| 6 |
|
| 7 |
My gratitude goes to my sponsors, a16z and Microsoft for Startups.
|
| 8 |
|
|
|
|
|
|
|
| 9 |
After first training Samantha on mistral-instruct, and seeing how she interacts, I felt that training on the base model would provide a more genuine Samantha experience. So I trained this one.
|
| 10 |
|
| 11 |
NEW! This Samantha is trained using ChatML prompt format instead of Vicuna-1.1. All of my future models will use ChatML prompt format.
|
|
|
|
| 6 |
|
| 7 |
My gratitude goes to my sponsors, a16z and Microsoft for Startups.
|
| 8 |
|
| 9 |
+
Join our Discord! https://discord.gg/cognitivecomputations
|
| 10 |
+
|
| 11 |
After first training Samantha on mistral-instruct, and seeing how she interacts, I felt that training on the base model would provide a more genuine Samantha experience. So I trained this one.
|
| 12 |
|
| 13 |
NEW! This Samantha is trained using ChatML prompt format instead of Vicuna-1.1. All of my future models will use ChatML prompt format.
|