Update README.md
Browse files
README.md
CHANGED
|
@@ -6,8 +6,9 @@ language:
|
|
| 6 |
---
|
| 7 |
# Model Card
|
| 8 |
|
| 9 |
-
This model is pretrained as a reference baseline to the Based model provided here: https://huggingface.co/hazyresearch/based-1b-50b
|
| 10 |
-
|
|
|
|
| 11 |
|
| 12 |
A WandB report for training is here: https://api.wandb.ai/links/hazy-research/ggo9rst2
|
| 13 |
|
|
|
|
| 6 |
---
|
| 7 |
# Model Card
|
| 8 |
|
| 9 |
+
This model is pretrained as a reference baseline to the Based model provided here: https://huggingface.co/hazyresearch/based-1b-50b.
|
| 10 |
+
|
| 11 |
+
Both checkpoints are pretrained on **50Bn tokens*** of the Pile in the exact same data order using next token prediction.
|
| 12 |
|
| 13 |
A WandB report for training is here: https://api.wandb.ai/links/hazy-research/ggo9rst2
|
| 14 |
|