Update README.md
Browse files
README.md
CHANGED
|
@@ -55,11 +55,6 @@ In addition, Doge uses Dynamic Mask Attention as sequence transformation and can
|
|
| 55 |
> All evaluations are done using five-shot settings, without additional training on the benchmarks.
|
| 56 |
|
| 57 |
|
| 58 |
-
**Procedure**:
|
| 59 |
-
|
| 60 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/loser_cheems/huggingface/runs/p8x93v5l)
|
| 61 |
-
|
| 62 |
-
|
| 63 |
**Environment**:
|
| 64 |
|
| 65 |
- Image: nvcr.io/nvidia/pytorch:24.12-py3
|
|
|
|
| 55 |
> All evaluations are done using five-shot settings, without additional training on the benchmarks.
|
| 56 |
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
**Environment**:
|
| 59 |
|
| 60 |
- Image: nvcr.io/nvidia/pytorch:24.12-py3
|