Ransaka commited on
Commit
80f1456
1 Parent(s): fb6bede

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -6
README.md CHANGED
@@ -24,11 +24,6 @@ language:
24
  # sinhala-gpt2
25
 
26
  This particular model has undergone fine-tuning based on the [gpt2](https://huggingface.co/gpt2) architecture, utilizing a dataset of Sinhala NEWS from various sources.
27
- Even though this is quite simple to train, it is still capable of generating news articles that are identical. Take, for example, the following samples(Some of them are hilarious though :D):
28
- - "ඔබ විසින් මෙම විරෝධතාව සංවිධානය කර තිබුණේ නැහැ කියලා හිටපු ජනාධිපති මහ"
29
- - "දුර්ලභ ගණයේ විශ්වවිද්යාල ප්රතිපාදන කොමිෂන් සභාවේ සභාපති මහාචාර්ය ජී එල්"
30
-
31
- ⚠️ Since the dataset used for this model is mostly composed of news articles, it is heavily biased toward generating news content. This bias may become apparent during the generation process.
32
 
33
  ## Training procedure
34
  The model was trained for 12+ hours on Kaggle GPUs.
@@ -40,7 +35,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM,pipeline
40
 
41
  tokenizer = AutoTokenizer.from_pretrained("Ransaka/sinhala-gpt2")
42
  model = AutoModelForCausalLM.from_pretrained("Ransaka/sinhala-gpt2")
43
- generator("දුර") #දුර ඈත පාසැල් වියේ පසුවූයේ මෙම සිද්ධිය සම්බන්ධයෙන් විමර්ශන සිදුකරන බවයි
44
  ```
45
  or using git
46
  ```bash
 
24
  # sinhala-gpt2
25
 
26
  This particular model has undergone fine-tuning based on the [gpt2](https://huggingface.co/gpt2) architecture, utilizing a dataset of Sinhala NEWS from various sources.
 
 
 
 
 
27
 
28
  ## Training procedure
29
  The model was trained for 12+ hours on Kaggle GPUs.
 
35
 
36
  tokenizer = AutoTokenizer.from_pretrained("Ransaka/sinhala-gpt2")
37
  model = AutoModelForCausalLM.from_pretrained("Ransaka/sinhala-gpt2")
38
+ generator("දුර")
39
  ```
40
  or using git
41
  ```bash