Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,6 @@ language:
|
|
| 5 |
- code
|
| 6 |
datasets:
|
| 7 |
- open-phi/programming_books_llama
|
| 8 |
-
- open-phi/textbooks
|
| 9 |
tags:
|
| 10 |
- merge
|
| 11 |
- computer science
|
|
@@ -50,4 +49,6 @@ This model can also answer basic questions, without needing to do any fine-tunin
|
|
| 50 |
|
| 51 |
This model was also created as an attempt to fix the issue with V2 - the weights were prone to exploding gradients, making it difficult to fine-tune. This model should be easier to fine-tune, however, I have not tested it yet.
|
| 52 |
|
| 53 |
-
To get the best out of this model, I recommend installing it, and trying it out yourself, as the model's performance seems to degrade in the inference API.
|
|
|
|
|
|
|
|
|
| 5 |
- code
|
| 6 |
datasets:
|
| 7 |
- open-phi/programming_books_llama
|
|
|
|
| 8 |
tags:
|
| 9 |
- merge
|
| 10 |
- computer science
|
|
|
|
| 49 |
|
| 50 |
This model was also created as an attempt to fix the issue with V2 - the weights were prone to exploding gradients, making it difficult to fine-tune. This model should be easier to fine-tune, however, I have not tested it yet.
|
| 51 |
|
| 52 |
+
To get the best out of this model, I recommend installing it, and trying it out yourself, as the model's performance seems to degrade in the inference API.
|
| 53 |
+
|
| 54 |
+
Currently, there is another checkpoint to be released soon.
|