Commit
•
8a6b6e5
1
Parent(s):
9961f8c
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,7 @@ tags: []
|
|
| 6 |
# Model Card for Model ID
|
| 7 |
|
| 8 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
-
|
| 10 |
|
| 11 |
|
| 12 |
## Model Details
|
|
|
|
| 6 |
# Model Card for Model ID
|
| 7 |
|
| 8 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
Merged adapter of the checkpoints [chansurgeplus/OpenELM-270M-cosmopedia-openstax-checkpoint](https://huggingface.co/chansurgeplus/OpenELM-270M-cosmopedia-openstax-checkpoint), [chansurgeplus/OpenELM-270M-cosmopedia-wikihow-checkpoint](https://huggingface.co/chansurgeplus/OpenELM-270M-cosmopedia-wikihow-checkpoint), [chansurgeplus/OpenELM-270M-cosmopedia-khanacademy-checkpoint](https://huggingface.co/chansurgeplus/OpenELM-270M-cosmopedia-khanacademy-checkpoint), and [chansurgeplus/OpenELM-270M-dolly-15k-checkpoint](https://huggingface.co/chansurgeplus/OpenELM-270M-dolly-15k-checkpoint) using concatenation with weights (0.3662, 0.5202, 0.0700, 0.0436) respectively. These weights are derived w.r.t. the size of the dataset that the corresponding checkpoint was trained on against the cumulative dataset size for all of the checkpoints.
|
| 10 |
|
| 11 |
|
| 12 |
## Model Details
|