Update README.md

README.md

@@ -13,59 +13,6 @@ metrics:
 language:
 - en
 widget:
-  - text: |
-      import torch
-      from transformers import AutoTokenizer, AutoModelForSequenceClassification
-
-      checkpoint = "distilbert-base-uncased-finetuned-sst-2-english"
-      tokenizer = AutoTokenizer.from_pretrained(checkpoint)
-      model = AutoModelForSequenceClassification.from_pretrained(checkpoint)
-      sequences = ["I've been waiting for a HuggingFace course my whole life.", "So have I!"]
-
-      tokens = tokenizer(sequences, padding=True, truncation=True, return_tensors="pt")
-      output = model(**tokens)
-    example_title: Example One
-
-  - text: |
-      import torch
-      from tqdm.auto import tqdm
-
-      device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
-      model.to(device)
-
-      progress_bar = tqdm(range(num_training_steps))
-
-      model.train()
-      for epoch in range(num_epochs):
-          for batch in train_dataloader:
-              batch = {k: v.to(device) for k, v in batch.items()}
-              outputs = model(**batch)
-              loss = outputs.loss
-              loss.backward()
-
-              optimizer.step()
-              lr_scheduler.step()
-              optimizer.zero_grad()
-              progress_bar.update(1)
-    example_title: Example Two
-
-  - text: |
-      import evaluate
-
-      metric = evaluate.load("glue", "mrpc")
-      model.eval()
-      for batch in eval_dataloader:
-          batch = {k: v.to(device) for k, v in batch.items()}
-          with torch.no_grad():
-              outputs = model(**batch)
-
-          logits = outputs.logits
-          predictions = torch.argmax(logits, dim=-1)
-          metric.add_batch(predictions=predictions, references=batch["labels"])
-
-      metric.compute()
-    example_title: Example Three
-
   - text: |
       git lfs install
       huggingface-cli lfs-enable-largefiles .
@@ -73,7 +20,7 @@ widget:
       git add .
       git commit -a -m "add fp32 chkpt"
       git push
-    example_title: Example Four
+    example_title: bash
 
   - text: |
       export interface DocumentParams {
@@ -97,7 +44,99 @@ widget:
           this.metadata = fields?.metadata ?? {};
         }
       }
-    example_title: Example Five
+    example_title: js
+  - text: |
+      def merge(left, right):
+          if len(left) == 0:
+              return right
+
+          if len(right) == 0:
+              return left
+
+          result = []
+          index_left = index_right = 0
+
+          while len(result) < len(left) + len(right):
+              if left[index_left] <= right[index_right]:
+                  result.append(left[index_left])
+                  index_left += 1
+              else:
+                  result.append(right[index_right])
+                  index_right += 1
+
+              if index_right == len(right):
+                  result += left[index_left:]
+                  break
+
+              if index_left == len(left):
+                  result += right[index_right:]
+                  break
+
+          return result
+    example_title: merge
+
+  - text: |
+      import pandas as pd
+      import plotly.graph_objects as go
+
+      df = pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/2014_apple_stock.csv')
+
+      fig = go.Figure(go.Scatter(x = df['AAPL_x'], y = df['AAPL_y'],
+                        name='Share Prices (in USD)'))
+
+      fig.update_layout(title='Apple Share Prices over time (2014)',
+                         plot_bgcolor='rgb(230, 230,230)',
+                         showlegend=True)
+
+      fig.show()
+    example_title: plot
+  - text: |
+      from spellchecker import SpellChecker
+
+      spell = SpellChecker()
+
+      def check_word_spelling(word: str):
+          misspelled = spell.unknown([word])
+          return len(misspelled) == 0
+
+      def eval_and_replace(text: str, match_token: str = "- "):
+          if match_token not in text:
+              return text
+          else:
+              while True:
+                  full_before_text = text.split(match_token, maxsplit=1)[0]
+                  before_text = [
+                      char for char in full_before_text.split()[-1] if char.isalpha()
+                  ]
+                  before_text = "".join(before_text)
+                  full_after_text = text.split(match_token, maxsplit=1)[-1]
+                  after_text = [char for char in full_after_text.split()[0] if char.isalpha()]
+                  after_text = "".join(after_text)
+                  full_text = before_text + after_text
+                  if check_word_spelling(full_text):
+                      text = full_before_text + full_after_text
+                  else:
+                      text = full_before_text + " " + full_after_text
+                  if match_token not in text:
+                      break
+              return text
+
+      text = "I- am- a go- od- boy"
+      eval_and_replace(text)
+    example_title: speel check
+  - text: |
+      import torch
+      from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+      checkpoint = "distilbert-base-uncased-finetuned-sst-2-english"
+      tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+      model = AutoModelForSequenceClassification.from_pretrained(checkpoint)
+      sequences = ["I've been waiting for a HuggingFace course my whole life.", "So have I!"]
+
+      tokens = tokenizer(sequences, padding=True, truncation=True, return_tensors="pt")
+      output = model(**tokens)
+    example_title: model inference
+
 inference:
   parameters:
     max_length: 96