initial model uploaded

README.md

@@ -0,0 +1,89 @@
+---
+pipeline_tag: paraphrasing
+tags:
+- paraphrasing
+language: en
+license: apache-2.0
+---
+
+## Model in Action 🚀
+
+```python
+import torch
+from transformers import T5ForConditionalGeneration,T5Tokenizer
+
+
+def set_seed(seed):
+  torch.manual_seed(seed)
+  if torch.cuda.is_available():
+    torch.cuda.manual_seed_all(seed)
+
+set_seed(42)
+
+model = T5ForConditionalGeneration.from_pretrained('valurank/t5-paraphraser')
+tokenizer = T5Tokenizer.from_pretrained('valurank/t5-paraphraser')
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+print ("device ",device)
+model = model.to(device)
+
+sentence = "Which course should I take to get started in data science?"
+# sentence = "What are the ingredients required to bake a perfect cake?"
+# sentence = "What is the best possible approach to learn aeronautical engineering?"
+# sentence = "Do apples taste better than oranges in general?"
+
+
+text =  "paraphrase: " + sentence + " </s>"
+
+
+max_len = 256
+
+encoding = tokenizer.encode_plus(text,pad_to_max_length=True, return_tensors="pt")
+input_ids, attention_masks = encoding["input_ids"].to(device), encoding["attention_mask"].to(device)
+
+
+# set top_k = 50 and set top_p = 0.95 and num_return_sequences = 3
+beam_outputs = model.generate(
+    input_ids=input_ids, attention_mask=attention_masks,
+    do_sample=True,
+    max_length=256,
+    top_k=120,
+    top_p=0.98,
+    early_stopping=True,
+    num_return_sequences=10
+)
+
+
+print ("\nOriginal Question ::")
+print (sentence)
+print ("\n")
+print ("Paraphrased Questions :: ")
+final_outputs =[]
+for beam_output in beam_outputs:
+    sent = tokenizer.decode(beam_output, skip_special_tokens=True,clean_up_tokenization_spaces=True)
+    if sent.lower() != sentence.lower() and sent not in final_outputs:
+        final_outputs.append(sent)
+
+for i, final_output in enumerate(final_outputs):
+    print("{}: {}".format(i, final_output))
+
+```
+## Output
+```
+Original Question ::
+Which course should I take to get started in data science?
+
+
+Paraphrased Questions :: 
+0: What should I learn to become a data scientist?
+1: How do I get started with data science?
+2: How would you start a data science career?
+3: How can I start learning data science?
+4: How do you get started in data science?
+5: What's the best course for data science?
+6: Which course should I start with for data science?
+7: What courses should I follow to get started in data science?
+8: What degree should be taken by a data scientist?
+9: Which course should I follow to become a Data Scientist?
+```
+

config.json

@@ -0,0 +1,51 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "vocab_size": 32128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47909fb9fa11cf95db9c501c120ff2212cd6c89cf80e00e811cd6239d31d9719
+size 891691413

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 512}