Thacio Garcia Scandaroli
commited on
Commit
·
ed9deac
1
Parent(s):
26a06e5
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
language:
|
4 |
+
- pt
|
5 |
+
tags:
|
6 |
+
- t5
|
7 |
+
- ul2
|
8 |
+
- pt
|
9 |
+
- pt-br
|
10 |
+
datasets:
|
11 |
+
- allenai/c4
|
12 |
+
library_name: transformers
|
13 |
+
---
|
14 |
+
|
15 |
+
## Model Details
|
16 |
+
|
17 |
+
### Model Description
|
18 |
+
|
19 |
+
<!-- Provide a longer summary of what this model is. -->
|
20 |
+
|
21 |
+
ULT5-pt é um modelo de arquitetura T5-v1.1 treinado com o framework UL2 - [Unifying Language Learning Paradigms](https://arxiv.org/abs/2205.05131v1), que utiliza Mixture-of-Denoisers (MoD), o qual combina o objetivo de Causal Language Modeling (CLM) com Span Corruption.
|
22 |
+
|
23 |
+
- **Developed by:** Thacio Garcia Scandaroli
|
24 |
+
- **Model type:** T5
|
25 |
+
- **Language(s) (NLP):** Português
|
26 |
+
- **License:** MIT
|
27 |
+
|
28 |
+
## Pré-treino e especificidades do modelo
|
29 |
+
|
30 |
+
O modelo foi treinado com uma parte do corpus C4 em português utilizando o UL2 (https://huggingface.co/google/ul2), utilizando *R-Denoising*, *S-Denoising* e *X-Denoising*, e com dropout 0.0.
|
31 |
+
|
32 |
+
De forma diferente, não se utilizou token de prefixo para o *S-Denoising*. Para o *R-Denoising* e o *X-Denoising*, foram utilizados, respectivamente, os tokens <|NLU|> e <|NLG|>.
|
33 |
+
|
34 |
+
Utilizou-se uma janela de contexto para 1024 tokens e um tokenizador do GPT2 com vocabulário em português treinado com o wikipedia, aumentando a quantidade de texto que pode ser processada.
|
35 |
+
|
36 |
+
|
37 |
+
## Uses
|
38 |
+
|
39 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
40 |
+
|
41 |
+
### Direct Use
|
42 |
+
|
43 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
44 |
+
|
45 |
+
[More Information Needed]
|
46 |
+
|
47 |
+
|
48 |
+
### Out-of-Scope Use
|
49 |
+
|
50 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
51 |
+
|
52 |
+
[More Information Needed]
|
53 |
+
|
54 |
+
## Bias, Risks, and Limitations
|
55 |
+
|
56 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
57 |
+
|
58 |
+
[More Information Needed]
|
59 |
+
|
60 |
+
### Recommendations
|
61 |
+
|
62 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
63 |
+
|
64 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
65 |
+
|
66 |
+
## How to Get Started with the Model
|
67 |
+
|
68 |
+
Use the code below to get started with the model.
|
69 |
+
|
70 |
+
[More Information Needed]
|
71 |
+
|
72 |
+
## Citation
|
73 |
+
|
74 |
+
@misc{ult52023,
|
75 |
+
author = {Thacio Garcia Scandaroli},
|
76 |
+
title = {ULT5-pt: Portuguese Language Model using UL2},
|
77 |
+
year = {2023},
|
78 |
+
}
|