Update README.md

README.md

@@ -1,14 +1,13 @@
 ---
 language: 
-- mk
+- gr
 thumbnail: https://huggingface.co/macedonizer/mk-roberta-base/blaze-koneski.jpg
 license: apache-2.0
 datasets:
-- wiki-mk
-- time-mk-news-2010-2015
+- wiki-gr
 ---
 
-# mk-gpt2
+# gr-gpt2
 Test the whole generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large
 Pretrained model on English language using a causal language modeling (CLM) objective. It was introduced in
 [this paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf)
@@ -32,14 +31,14 @@ Here is how to use this model to get the features of a given text in PyTorch:
 import random
 from transformers import AutoTokenizer, AutoModelWithLMHead
 
-tokenizer = AutoTokenizer.from_pretrained('macedonizer/mk-gpt2') \
-model = AutoModelWithLMHead.from_pretrained('macedonizer/mk-gpt2')
+tokenizer = AutoTokenizer.from_pretrained('macedonizer/gr-gpt2') \
+nmodel = AutoModelWithLMHead.from_pretrained('macedonizer/gr-gpt2')
 
-input_text = 'Скопје е '
+input_text = 'Η Αθήνα είναι'
 
 if len(input_text) == 0: \
     encoded_input = tokenizer(input_text, return_tensors="pt") \
-    output = model.generate( \
+        output = model.generate( \
         bos_token_id=random.randint(1, 50000), \
         do_sample=True, \
         top_k=50, \
@@ -50,17 +49,16 @@ if len(input_text) == 0: \
 else: \
     encoded_input = tokenizer(input_text, return_tensors="pt") \
     output = model.generate( \
-        **encoded_input, \
-        bos_token_id=random.randint(1, 50000), \
-        do_sample=True, \
-        top_k=50, \
-        max_length=1024, \
-        top_p=0.95, \
-        num_return_sequences=1, \
-    )
+    **encoded_input, \
+    bos_token_id=random.randint(1, 50000), \
+    do_sample=True, \
+    top_k=50, \
+    max_length=1024, \
+    top_p=0.95, \
+    num_return_sequences=1, \
+)
 
-decoded_output = [] \
-for sample in output: \
-    decoded_output.append(tokenizer.decode(sample, skip_special_tokens=True))
+decoded_output = [] \\nfor sample in output: \
+decoded_output.append(tokenizer.decode(sample, skip_special_tokens=True))
 
 print(decoded_output)