Update README.md
Browse files
README.md
CHANGED
|
@@ -6,4 +6,12 @@ At Adept, we’re working towards an AI agent that can help people do anything t
|
|
| 6 |
|
| 7 |
We trained it from scratch using a context size of 16K. Many LM use cases are context-bound; our model has 4 times the context size of LLaMA2 and 8 times that of GPT-3, MPT, etc.
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
See https://www.adept.ai/blog/persimmon-8b for more info
|
|
|
|
| 6 |
|
| 7 |
We trained it from scratch using a context size of 16K. Many LM use cases are context-bound; our model has 4 times the context size of LLaMA2 and 8 times that of GPT-3, MPT, etc.
|
| 8 |
|
| 9 |
+
This is a chat finetuned version of the base model. The best prompt to use is:
|
| 10 |
+
|
| 11 |
+
human: [some query]
|
| 12 |
+
|
| 13 |
+
adept:
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
See https://www.adept.ai/blog/persimmon-8b for more info
|