RichardErkhov
commited on
Commit
•
6b59b32
1
Parent(s):
9c5776b
uploaded readme
Browse files
README.md
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Quantization made by Richard Erkhov.
|
2 |
+
|
3 |
+
[Github](https://github.com/RichardErkhov)
|
4 |
+
|
5 |
+
[Discord](https://discord.gg/pvy7H8DZMG)
|
6 |
+
|
7 |
+
[Request more models](https://github.com/RichardErkhov/quant_request)
|
8 |
+
|
9 |
+
|
10 |
+
mbart-large-en-ro - bnb 8bits
|
11 |
+
- Model creator: https://huggingface.co/facebook/
|
12 |
+
- Original model: https://huggingface.co/facebook/mbart-large-en-ro/
|
13 |
+
|
14 |
+
|
15 |
+
|
16 |
+
|
17 |
+
Original model description:
|
18 |
+
---
|
19 |
+
tags:
|
20 |
+
- translation
|
21 |
+
|
22 |
+
language:
|
23 |
+
- en
|
24 |
+
- ro
|
25 |
+
|
26 |
+
license: mit
|
27 |
+
---
|
28 |
+
### mbart-large-en-ro
|
29 |
+
This is mbart-large-cc25, finetuned on wmt_en_ro.
|
30 |
+
|
31 |
+
It scores BLEU 28.1 without post processing and BLEU 38 with postprocessing. Instructions in `romanian_postprocessing.md`
|
32 |
+
|
33 |
+
Original Code: https://github.com/pytorch/fairseq/tree/master/examples/mbart
|
34 |
+
|
35 |
+
Docs: https://huggingface.co/transformers/master/model_doc/mbart.html
|
36 |
+
|
37 |
+
Finetuning Code: examples/seq2seq/finetune.py (as of Aug 20, 2020)
|
38 |
+
|
39 |
+
|