Update README.md

README.md

@@ -1,53 +1,28 @@
 erfan226/persian-t5-paraphraser
 
-This is a paraphrase model that works on the Persian language. It is based on [the monolingual T5 model](https://huggingface.co/Ahmad/parsT5-base)
-language:
-- {fa}
-# Usage (Sentence-Transformers)
+This is a paraphrasing model for the Persian language. It is based on [the monolingual T5 model for Persian](https://huggingface.co/Ahmad/parsT5-base)
 
-```python
-
-pip install -U sentence-transformers
-Then you can use the model like this:
-
-from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
-
-model = SentenceTransformer('sentence-transformers/paraphrase-MiniLM-L6-v2')
-embeddings = model.encode(sentences)
-print(embeddings)
-Usage (HuggingFace Transformers)
-Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
-
-from transformers import AutoTokenizer, AutoModel
-import torch
+# Usage
 
+```python
 
-#Mean Pooling - Take attention mask into account for correct averaging
-def mean_pooling(model_output, attention_mask):
-    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
-    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
-    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
-
-
-# Sentences we want sentence embeddings for
-sentences = ['This is an example sentence', 'Each sentence is converted']
-
-# Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-MiniLM-L6-v2')
-model = AutoModel.from_pretrained('sentence-transformers/paraphrase-MiniLM-L6-v2')
-
-# Tokenize sentences
-encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+>>> pip install transformers
+>>> from transformers import (T5ForConditionalGeneration, AutoTokenizer)
+>>> import torch
 
-# Compute token embeddings
-with torch.no_grad():
-    model_output = model(**encoded_input)
+model_path = 'erfan226/persian-t5-paraphraser'
+model = T5ForConditionalGeneration.from_pretrained(model_path)
+tokenizer = AutoTokenizer.from_pretrained(model_path)
 
-# Perform pooling. In this case, max pooling.
-sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+def paraphrase(text):
+    input = tokenizer(text, return_tensors='pt', padding=True).to(model.device)
+    max_size = int(input.input_ids.shape[1] * 1.5 + 10)
+    out = model.generate(**input, encoder_no_repeat_ngram_size=4, do_sample=False, num_beams=10, max_length=max_size, no_repeat_ngram_size=4,)
+    return tokenizer.decode(out[0], skip_special_tokens=True)
 
-print("Sentence embeddings:")
-print(sentence_embeddings)
+for text1, text2 in zip(x, y):
+    print("Original:", text1)
+    print("Paraphrase:", paraphrase(text1))
+    print("Original Paraphrase:", text2)
 
 ```