Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,34 @@
|
|
| 1 |
---
|
| 2 |
license: openrail
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: openrail
|
| 3 |
---
|
| 4 |
+
# Model Card for mpyt5_e15
|
| 5 |
+
|
| 6 |
+
<!-- Provide a quick summary of what the model is/does. [Optional] -->
|
| 7 |
+
事前に自然言語だけでなくPythonを学習したモデル
|
| 8 |
+
|
| 9 |
+
# Training Details
|
| 10 |
+
|
| 11 |
+
## Training Data
|
| 12 |
+
|
| 13 |
+
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 14 |
+
|
| 15 |
+
Python Code (1.05GB)
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Training Procedure
|
| 19 |
+
|
| 20 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 21 |
+
|
| 22 |
+
MLM
|
| 23 |
+
python vocab (https://huggingface.co/kkuramitsu/mt5-pytoken)
|
| 24 |
+
|
| 25 |
+
### Preprocessing
|
| 26 |
+
|
| 27 |
+
mT5 + Python
|
| 28 |
+
|
| 29 |
+
### Speeds, Sizes, Times
|
| 30 |
+
|
| 31 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 32 |
+
|
| 33 |
+
mT5-small(300M Paramators)
|
| 34 |
+
max_length = 128
|