Teja-Gollapudi
commited on
Commit
•
6e49447
1
Parent(s):
3b9adc3
Update README.md
Browse files
README.md
CHANGED
@@ -67,8 +67,6 @@ This way, the model can better understand the relationship between different par
|
|
67 |
## Drawbacks
|
68 |
|
69 |
- The model was trained on a partially trained Open-LLaMA checkpoint. (300B tokens).
|
70 |
-
- The model is inconsistent with outputting '\n' tokens as majority of the dataset is obtained from [mosaicml/dolly_hhrlhf](https://huggingface.co/datasets/mosaicml/dolly_hhrlhf) and that dataset removed newline characters from responses.
|
71 |
-
|
72 |
|
73 |
## Evaluation
|
74 |
|
|
|
67 |
## Drawbacks
|
68 |
|
69 |
- The model was trained on a partially trained Open-LLaMA checkpoint. (300B tokens).
|
|
|
|
|
70 |
|
71 |
## Evaluation
|
72 |
|