Add library name, pipeline tag and license
#1
by
nielsr HF Staff - opened
README.md
CHANGED
|
@@ -3,7 +3,11 @@ datasets:
|
|
| 3 |
- HuggingFaceTB/smollm-corpus
|
| 4 |
language:
|
| 5 |
- en
|
|
|
|
|
|
|
|
|
|
| 6 |
---
|
|
|
|
| 7 |
# Outlier-Safe Pre-Training
|
| 8 |
|
| 9 |
[](https://arxiv.org/abs/2506.19697)
|
|
@@ -177,7 +181,6 @@ The models were trained on 1 trillion tokens, following the pre-training recipe
|
|
| 177 |
</table>
|
| 178 |
†Model configuration that disables decoupled embedding optimization by training with Muon optimizer without Adam optimization on embedding layers
|
| 179 |
|
| 180 |
-
|
| 181 |
## Training
|
| 182 |
|
| 183 |
### Model
|
|
|
|
| 3 |
- HuggingFaceTB/smollm-corpus
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
library_name: transformers
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
---
|
| 10 |
+
|
| 11 |
# Outlier-Safe Pre-Training
|
| 12 |
|
| 13 |
[](https://arxiv.org/abs/2506.19697)
|
|
|
|
| 181 |
</table>
|
| 182 |
†Model configuration that disables decoupled embedding optimization by training with Muon optimizer without Adam optimization on embedding layers
|
| 183 |
|
|
|
|
| 184 |
## Training
|
| 185 |
|
| 186 |
### Model
|