Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: openrail
|
| 3 |
+
datasets:
|
| 4 |
+
- nthngdy/oscar
|
| 5 |
+
language:
|
| 6 |
+
- kk
|
| 7 |
+
tags:
|
| 8 |
+
- summarization
|
| 9 |
+
- translation
|
| 10 |
+
pipeline_tag: text2text-generation
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
This model trains [T5-V1_1-base](https://huggingface.co/google/t5-v1_1-base) on the Qazaq dataset of [Oscar-mini](https://huggingface.co/datasets/nthngdy/oscar-mini). Note that the original configuration is slightly change (dropout is set to 0).
|
| 14 |
+
|
| 15 |
+
The official [run_t5_mlm_flax.py](https://github.com/huggingface/transformers/blob/master/examples/flax/language-modeling/run_t5_mlm_flax.py) is copied into the repository and is run using the hyperparameters as defined in *run_t5.sh*.
|