Update README.md

README.md

@@ -26,17 +26,29 @@ tokenizer = AutoTokenizer.from_pretrained("humarin/chatgpt_paraphraser_on_T5_bas
 
 model = AutoModelForSeq2SeqLM.from_pretrained("humarin/chatgpt_paraphraser_on_T5_base").to(device)
 
-def paraphrase(text, max_length=128, num_return_sequences=5, num_beams=25, temperature=0.7):
+def paraphrase(
+    question,
+    num_beams=5,
+    num_beam_groups=5,
+    num_return_sequences=5,
+    repetition_penalty=10.0,
+    diversity_penalty=3.0,
+    no_repeat_ngram_size=2,
+    temperature=0.7,
+    max_length=128
+):
     input_ids = tokenizer(
-        f'paraphrase: {text}',
+        f'paraphrase: {question}',
         return_tensors="pt", padding="longest",
         max_length=max_length,
         truncation=True,
-    ).input_ids.to(device)
+    ).input_ids
     
     outputs = model.generate(
-        input_ids, temperature=temperature, repetition_penalty=1.5,
-        num_return_sequences=num_return_sequences, no_repeat_ngram_size=5, num_beams=num_beams, max_length=max_length
+        input_ids, temperature=temperature, repetition_penalty=repetition_penalty,
+        num_return_sequences=num_return_sequences, no_repeat_ngram_size=no_repeat_ngram_size,
+        num_beams=num_beams, num_beam_groups=num_beam_groups,
+        max_length=max_length, diversity_penalty=diversity_penalty
     )
 
     res = tokenizer.batch_decode(outputs, skip_special_tokens=True)
@@ -53,11 +65,11 @@ paraphrase(text)
 ```
 **Output:**
 ```python
-['What are some of the must-visit places in New York?',
- 'Which are the top destinations to explore in New York?',
- 'What are some of the must-visit spots in New York?',
- 'What are some of the must-see places in New York?',
- 'Which places should I not miss when visiting New York?']
+['Which places should I not miss when visiting New York?',
+ 'What are the top-rated tourist destinations in New York?',
+ 'Where should I go sightseeing in New York?',
+ 'Can you suggest some must-see places in New York?',
+ 'What are some must-see places in New York?']
 ```
 
 **Input:**
@@ -67,17 +79,17 @@ paraphrase(text)
 ```
 **Output:**
 ```python
-['In May and June 2000, Rammstein recorded Mutter in the south of France, with the album being mixed in Stockholm in October of the same year.',
- 'In May and June 2000, Rammstein recorded Mutter in the south of France, with the album being mixed in Stockholm in October of that year.',
- 'In May and June 2000, Rammstein recorded Mutter, his album, in the south of France, with mixing taking place in Stockholm in October of the same year.',
- 'In May and June 2000, Rammstein filmed the recording of his album Mutter in the south of France, with the mixing process taking place in Stockholm in October of the same year.',
- 'In May and June 2000, Rammstein recorded Mutter in the south of France, with mixing taking place in Stockholm in October of the same year.']
+['In May and June 2000, Rammstein filmed the album Mutter in the south of France, with mixing taking place in Stockholm in October of that year.',
+ 'The album Mutter by Rammstein was recorded in the south of France during May and June 2000, with subsequent mixing taking place in Stockholm in October of that year.',
+ 'Mutter, the album by Rammstein, was recorded in the south of France during May and June 2000, with mixing taking place at Stockholm in October of that year.',
+ "Rammstein's album Mutter was produced during May and June 2000 in southern France, with mixing taking place in Stockholm from October.",
+ 'In May and June 2000, Rammstein recorded Mutter in southern France, followed by mixing it in Stockholm in October of the same year.']
 ```
 
 
 **Train parameters:**
 ```python
-epochs = 3
+epochs = 3.5
 batch_size = 64
 max_length = 128
 lr = 5e-5