README.md

README.md

@@ -1,3 +1,60 @@
 ---
-pipeline_tag: text-generation
----
+language: vi
+tags:
+- vi
+- vietnamese
+- gpt2
+- text-generation
+- lm
+- nlp
+datasets:
+- VN-Literature
+widget:
+- text: >-
+    Hôm ấy, cụ Bá ông quả quyết mở ví tiền để trả cho anh lái chó cái giấy bạc
+    một đồng.
+---
+inference:
+  parameters:
+    max_length: 500
+    do_sample: True
+    temperature: 0.8
+
+# GPT-2
+
+The GPT2 model is pre-trained on the writing style of Vu Trong Phung
+
+# How to use the model
+
+~~~~
+from transformers import GPT2Tokenizer, GPT2LMHeadModel
+
+tokenizer = GPT2Tokenizer.from_pretrained("Khoa/VN-Literature-Generation")
+model = GPT2LMHeadModel.from_pretrained("Khoa/VN-Literature-Generation")
+
+
+text = "Mùa thu lá vàng rơi"
+input_ids = tokenizer.encode(text, return_tensors='pt')
+max_length = 300
+model.to('cpu')
+sample_outputs = model.generate(input_ids,pad_token_id=tokenizer.eos_token_id,
+                                   do_sample=True,
+                                   max_length=max_length,
+                                   min_length=max_length,
+                                   top_k=40,
+                                   num_beams=5,
+                                   early_stopping=True,
+                                   no_repeat_ngram_size=2,
+                                   num_return_sequences=3)
+
+for i, sample_output in enumerate(sample_outputs):
+    print(">> Generated text {}\n\n{}".format(i+1, tokenizer.decode(sample_output.tolist())))
+    print('\n---')
+
+~~~~
+
+
+## Author
+`
+Dong Dang Khoa
+`