HF staff

Automatic correction of README.md metadata for keys. Contact website@huggingface.co for any question 214c737 6 days ago

4.12 kB

---
language:
- tr
thumbnail:
tags:
- gpt2
- turkish
- aiwriter
- finetuned

license: apache-2.0
datasets:
- wikipedia-turkish
- custom-book-corpus
metrics:
- perplexity
- accuracy

widget:
- text: Bir zaman topu olan ama köpeği olmayan bir çocuk vardı. Parkta
  context: ''
- text: 'Uzun uzun sahile doğru baktı. Düşündüklerinden '
  context: ''
- text: Çok uzun zaman önce galaksinin uzak bir köşesinde...
  context: ''
- text: "'Bugün kendimi çok hasta hissediyorum' dedi. Karşısında "
  context: ''
---

# Turkish AI Writer based on GPT2-Small
# Türkçe Yapay Zeka Yazarı

## Model description

This model is enhanced version of gpt2-small-turkish finetuned version. In addition to 28-10-2020 Wikipedia Turkish article dump this model is trained with more than 400 classic novels and plays in Turkish (Including Dostoyevski, Shaekspeare, Dumas)

Base work has been done on Pierre Guillou tutorial as on this page.
(https://github.com/piegu/fastai-projects/blob/master/finetuning-English-GPT2-any-language-Portuguese-HuggingFace-fastaiv2.ipynb) 

Note that Since Turkish language is not close to English as in Porteguese instead  of training last 2 layers, last 3 layers are trained.

Code is converted to work with Fastai 2.X .
Using Google Colab for training. 

Current accuracy 36.3 %  , Perplexity : 44.75

Demo (using CPU inference) is available on: http://www.metayazar.com 

Models are available:

* [gpt2-small-tuned-tr] (https://huggingface.co/gorkemgoknar/gpt2-small-turkish)
* [gpt2-small-turkish-writer] (https://huggingface.co/gorkemgoknar/gpt2-turkish-writer)


## Intended uses & limitations

#### How to use

#### Install

```python
from transformers import AutoTokenizer, AutoModelWithLMHead
import torch

tokenizer = AutoTokenizer.from_pretrained("gorkemgoknar/gpt2-turkish-writer")
model = AutoModelWithLMHead.from_pretrained("gorkemgoknar/gpt2-turkish-writer")

# Get sequence length max of 1024
tokenizer.model_max_length=1024 

model.eval()  # disable dropout (or leave in train mode to finetune)

```

#### Generate 1 word
```python
# input sequence
text = "Bu yazıyı bilgisayar yazdı."
inputs = tokenizer(text, return_tensors="pt") 

# model output
outputs = model(**inputs, labels=inputs["input_ids"])
loss, logits = outputs[:2]
predicted_index = torch.argmax(logits[0, -1, :]).item()
predicted_text = tokenizer.decode([predicted_index])

# results
print('input text:', text)
print('predicted text:', predicted_text)

# input text: 
# predicted text:  

```

#### Generate Full Sequence
```python
# input sequence
text = "Bu yazıyı bilgisayar yazdı."
inputs = tokenizer(text, return_tensors="pt")

# model output using Top-k sampling text generation method
sample_outputs = model.generate(inputs.input_ids,
                                pad_token_id=50256,
                                do_sample=True, 
                                max_length=50, # put the token number you want
                                top_k=40,
                                num_return_sequences=1)

# generated sequence
for i, sample_output in enumerate(sample_outputs):
    print(">> Generated text {}\n\n{}".format(i+1, tokenizer.decode(sample_output.tolist())))

# >> Generated text
#    

```

#### Limitations and bias

The training data used for this model come from Turkish Wikipedia and books. We know it contains a lot of unfiltered content from the internet, which is far from neutral. Also not much pre-processing was done on books hence chapter names and page numbers can be seen on some cases. This is a work in progress.


## Training data

Wikipedia Turkish article dump as of 28-10-2020
Turkish book dataset of >400 classic novels

## Training procedure


## Eval results

| epoch	|train_loss	|valid_loss	|accuracy	|perplexity	|time   |
| ----- | --------      |---------      | ----------    | ---------     | ----- |
|0	|4.497828	|4.549605	|0.277328	|94.595070	|2:09:58|
|1	|4.503929	|4.519456	|0.275071	|91.785645	|2:04:30|
|2	|3.612716	|3.921146	|0.344802	|50.458256	|2:03:22|
|3	|3.777645	|4.072006	|0.326130	|58.674530	|1:56:14|
|4	|2.934462	|3.801303	|0.363719	|44.759476	|1:58:55|

Note: 1cycle rule training is used and epochs are at different times 
```



1	---
2	language:
3	- tr
4	thumbnail:
5	tags:
6	- gpt2
7	- turkish
8	- aiwriter
9	- finetuned
10
11	license: apache-2.0
12	datasets:
13	- wikipedia-turkish
14	- custom-book-corpus
15	metrics:
16	- perplexity
17	- accuracy
18
19	widget:
20	- text: Bir zaman topu olan ama köpeği olmayan bir çocuk vardı. Parkta
21	context: ''
22	- text: 'Uzun uzun sahile doğru baktı. Düşündüklerinden '
23	context: ''
24	- text: Çok uzun zaman önce galaksinin uzak bir köşesinde...
25	context: ''
26	- text: "'Bugün kendimi çok hasta hissediyorum' dedi. Karşısında "
27	context: ''
28	---
29
30	# Turkish AI Writer based on GPT2-Small
31	# Türkçe Yapay Zeka Yazarı
32
33	## Model description
34
35	This model is enhanced version of gpt2-small-turkish finetuned version. In addition to 28-10-2020 Wikipedia Turkish article dump this model is trained with more than 400 classic novels and plays in Turkish (Including Dostoyevski, Shaekspeare, Dumas)
36
37	Base work has been done on Pierre Guillou tutorial as on this page.
38	(https://github.com/piegu/fastai-projects/blob/master/finetuning-English-GPT2-any-language-Portuguese-HuggingFace-fastaiv2.ipynb)
39
40	Note that Since Turkish language is not close to English as in Porteguese instead of training last 2 layers, last 3 layers are trained.
41
42	Code is converted to work with Fastai 2.X .
43	Using Google Colab for training.
44
45	Current accuracy 36.3 % , Perplexity : 44.75
46
47	Demo (using CPU inference) is available on: http://www.metayazar.com
48
49	Models are available:
50
51	* [gpt2-small-tuned-tr] (https://huggingface.co/gorkemgoknar/gpt2-small-turkish)
52	* [gpt2-small-turkish-writer] (https://huggingface.co/gorkemgoknar/gpt2-turkish-writer)
53
54
55	## Intended uses & limitations
56
57	#### How to use
58
59	#### Install
60
61	```python
62	from transformers import AutoTokenizer, AutoModelWithLMHead
63	import torch
64
65	tokenizer = AutoTokenizer.from_pretrained("gorkemgoknar/gpt2-turkish-writer")
66	model = AutoModelWithLMHead.from_pretrained("gorkemgoknar/gpt2-turkish-writer")
67
68	# Get sequence length max of 1024
69	tokenizer.model_max_length=1024
70
71	model.eval() # disable dropout (or leave in train mode to finetune)
72
73	```
74
75	#### Generate 1 word
76	```python
77	# input sequence
78	text = "Bu yazıyı bilgisayar yazdı."
79	inputs = tokenizer(text, return_tensors="pt")
80
81	# model output
82	outputs = model(**inputs, labels=inputs["input_ids"])
83	loss, logits = outputs[:2]
84	predicted_index = torch.argmax(logits[0, -1, :]).item()
85	predicted_text = tokenizer.decode([predicted_index])
86
87	# results
88	print('input text:', text)
89	print('predicted text:', predicted_text)
90
91	# input text:
92	# predicted text:
93
94	```
95
96	#### Generate Full Sequence
97	```python
98	# input sequence
99	text = "Bu yazıyı bilgisayar yazdı."
100	inputs = tokenizer(text, return_tensors="pt")
101
102	# model output using Top-k sampling text generation method
103	sample_outputs = model.generate(inputs.input_ids,
104	pad_token_id=50256,
105	do_sample=True,
106	max_length=50, # put the token number you want
107	top_k=40,
108	num_return_sequences=1)
109
110	# generated sequence
111	for i, sample_output in enumerate(sample_outputs):
112	print(">> Generated text {}\n\n{}".format(i+1, tokenizer.decode(sample_output.tolist())))
113
114	# >> Generated text
115	#
116
117	```
118
119	#### Limitations and bias
120
121	The training data used for this model come from Turkish Wikipedia and books. We know it contains a lot of unfiltered content from the internet, which is far from neutral. Also not much pre-processing was done on books hence chapter names and page numbers can be seen on some cases. This is a work in progress.
122
123
124	## Training data
125
126	Wikipedia Turkish article dump as of 28-10-2020
127	Turkish book dataset of >400 classic novels
128
129	## Training procedure
130
131
132	## Eval results
133
134	\| epoch \|train_loss \|valid_loss \|accuracy \|perplexity \|time \|
135	\| ----- \| -------- \|--------- \| ---------- \| --------- \| ----- \|
136	\|0 \|4.497828 \|4.549605 \|0.277328 \|94.595070 \|2:09:58\|
137	\|1 \|4.503929 \|4.519456 \|0.275071 \|91.785645 \|2:04:30\|
138	\|2 \|3.612716 \|3.921146 \|0.344802 \|50.458256 \|2:03:22\|
139	\|3 \|3.777645 \|4.072006 \|0.326130 \|58.674530 \|1:56:14\|
140	\|4 \|2.934462 \|3.801303 \|0.363719 \|44.759476 \|1:58:55\|
141
142	Note: 1cycle rule training is used and epochs are at different times
143	```
144
145