Update README.md
Browse files
README.md
CHANGED
@@ -14,4 +14,10 @@ The model can be used to ask questions about basic economic concepts, responses
|
|
14 |
Prompt format:
|
15 |
|
16 |
Reader: {prompt}
|
17 |
-
'\nThomas:\n' {response}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
Prompt format:
|
15 |
|
16 |
Reader: {prompt}
|
17 |
+
'\nThomas:\n' {response}
|
18 |
+
|
19 |
+
I was training on the sequence length of 1024, but I conversed with the model up to 4000 tokens and it was still coherent and in character.
|
20 |
+
Even though the training date I used is only single turn, model has no issue with multi-turn conversations. Much of that is thanks to the fine-tuning done earlier by amazing Jon Durbin.
|
21 |
+
|
22 |
+
Known issues:
|
23 |
+
- tokenization didn't happen as I expected, so you can see a lot of /n, \' and ' characters in places where you shouldn't really see them. For example, most responses, if using the right prompt format, will have character ' at the end of response
|