Add pipeline tag and paper link
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,18 +1,19 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
| 3 |
library_name: megatron-lm
|
|
|
|
| 4 |
tags:
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
- mlfoundations/dclm-baseline-1.0
|
| 11 |
---
|
| 12 |
|
| 13 |
# DRMoET checkpoints
|
| 14 |
|
| 15 |
-
|
| 16 |
|
| 17 |
**Project page:** <https://drmoet.github.io> **Code:** <https://github.com/MAPS-research/DRMoET>
|
| 18 |
|
|
|
|
| 1 |
---
|
| 2 |
+
datasets:
|
| 3 |
+
- mlfoundations/dclm-baseline-1.0
|
| 4 |
library_name: megatron-lm
|
| 5 |
+
license: mit
|
| 6 |
tags:
|
| 7 |
+
- mixture-of-experts
|
| 8 |
+
- moe
|
| 9 |
+
- distributionally-robust-optimization
|
| 10 |
+
- megatron
|
| 11 |
+
pipeline_tag: text-generation
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# DRMoET checkpoints
|
| 15 |
|
| 16 |
+
**Paper:** [Distributionally Robust Mixture-of-Experts Training](https://huggingface.co/papers/2610.07207)
|
| 17 |
|
| 18 |
**Project page:** <https://drmoet.github.io> **Code:** <https://github.com/MAPS-research/DRMoET>
|
| 19 |
|