wannaphong commited on
Commit
c4a0ee2
1 Parent(s): 4617ecb

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +54 -0
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Thai GPT Next
2
+
3
+ It is fine-tune the GPT-Neo model for Thai language.
4
+
5
+ GitHub: https://github.com/wannaphong/thaigpt-next
6
+
7
+ **Dataset for fine-tune this model**
8
+
9
+ - prachathai67k
10
+ - thaisum
11
+ - thai_toxicity_tweet
12
+ - wongnai reviews
13
+ - wisesight_sentiment
14
+ - TLC
15
+ - scb_mt_enth_2020 (Thai only)
16
+ - Thai wikipedia (date: 2021/06/20)
17
+
18
+ **Max Length:** 280
19
+
20
+ **Number of train lists**: 1,697,254 lists
21
+
22
+ **Number of training**: 2 ep
23
+
24
+ **training loss**: 0.285500
25
+
26
+ ## Model
27
+
28
+ - thaigpt-next-125m is fine-tune the GPT-NEO-125M model.
29
+
30
+ ## How to use
31
+
32
+ You can using it from huggingface or PyThaiNLP (in the future) for few-shot learning works or text generation (not recommended).
33
+
34
+ thaigpt-next-125m at huggingface model: https://huggingface.co/wannaphong/thaigpt-next-125m
35
+
36
+ ## License
37
+
38
+ > Copyright 2021 Wannaphong Phatthiyaphaibun
39
+ >
40
+ > Licensed under the Apache License, Version 2.0 (the "License");
41
+ > you may not use this file except in compliance with the License.
42
+ > You may obtain a copy of the License at
43
+ >
44
+ > http://www.apache.org/licenses/LICENSE-2.0
45
+ >
46
+ > Unless required by applicable law or agreed to in writing, software
47
+ > distributed under the License is distributed on an "AS IS" BASIS,
48
+ > WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
49
+ > See the License for the specific language governing permissions and
50
+ > limitations under the License.
51
+
52
+ ## Author
53
+
54
+ Wannaphong Phatthiyaphaibun