initial commit

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,37 @@
+---
+title: Nlp_course_hw_style_transfer
+emoji: 👁
+colorFrom: purple
+colorTo: purple
+sdk: streamlit
+app_file: app.py
+pinned: false
+---
+
+# Configuration
+
+`title`: _string_  
+Display title for the Space
+
+`emoji`: _string_  
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_  
+Can be either `gradio` or `streamlit`
+
+`sdk_version` : _string_  
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_  
+Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
+Path is relative to the root of the repository.
+
+`pinned`: _boolean_  
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,61 @@
+import streamlit as st
+import torch
+import torch.nn.functional as F
+
+
+st.set_page_config(page_title='Review improver', layout='centered')
+
+st.markdown('Hello!')
+
+
+# load the necessary models
+bert_mlm_positive, bert_mlm_negative, bert_classifier, tokenizer = torch.load('models.pt', map_location='cpu')
+
+
+def get_replacements(sentence: str, num_tokens, k_best, epsilon=1e-3):
+    inputs = tokenizer(sentence, return_tensors='pt')
+    tokens = inputs['input_ids'][0]
+
+    vocab_logits_positive = bert_mlm_positive(**inputs)['logits'][0]
+    vocab_probs_positive = F.softmax(vocab_logits_positive, dim=1)
+    probs_positive = vocab_probs_positive[torch.arange(len(tokens)), tokens]
+
+    vocab_logits_negative = bert_mlm_negative(**inputs)['logits'][0]
+    vocab_probs_negative = F.softmax(vocab_logits_negative, dim=1)
+    probs_negative = vocab_probs_negative[torch.arange(len(tokens)), tokens]
+
+    ratio = (probs_positive + epsilon) / (probs_negative + epsilon)
+    smallest_ratio_ids = torch.argsort(ratio)[:num_tokens]
+
+    replacements = []
+    for idx in smallest_ratio_ids:
+        new_tokens = torch.argsort(vocab_probs_positive[idx])[-k_best:]
+        for token in new_tokens:
+            cur_replacement = tokens.clone()
+            cur_replacement[idx] = token
+            replacements.append(cur_replacement)
+
+    replacements = [tokenizer.decode(replacement, skip_special_tokens=True) for replacement in replacements]
+
+    return replacements
+
+
+def modify_sentence(sentence, num_iters=3):
+    for _ in range(num_iters):
+        replacements = get_replacements(sentence, num_tokens=3, k_best=5)
+
+        classifier_inputs = tokenizer(replacements, padding=True, return_tensors='pt')
+        logits = bert_classifier(**classifier_inputs)['logits'][:, 1]
+
+        best_idx = torch.argmax(logits)
+        sentence = replacements[best_idx]
+
+    return sentence
+
+
+# here we will try to improve the review
+user_input = st.text_input('Enter your review here and we will try to improve it:')
+if user_input:
+    improved_review = modify_sentence(user_input)
+    st.markdown('Here is your improved review:')
+    st.markdown(improved_review)

models.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01d9dfab0f7d5c49a5d84976384e24d1108b4fc04f500b79ff5fbfec48faf82
+size 1315214587

requirements.txt

@@ -0,0 +1,3 @@
+streamlit
+torch
+transformers