Create README.md

README.md

@@ -0,0 +1,104 @@
+## Examples
+
+Here are some examples of how to use this model in Python:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("Rel8ed/cleantech-cls")
+model = AutoModelForCausalLM.from_pretrained("Rel8ed/cleantech-cls")
+
+input_prompt = "[METAKEYWORD] innovation, technology, clean energy [TITLE] innovative clean energy solutions [META]" \
+          "leading provider of clean energy solutions. [ABOUT] we are committed to reducing environmental impact through" \
+          "cutting-edge clean energy solutions. [HOME] welcome to our website where we explore innovative technologies for a sustainable future."
+
+inputs = tokenizer.encode(input_prompt, return_tensors='pt')
+output = model.generate(inputs, max_length=50, num_return_sequences=5)
+
+print("Generated text:")
+for i, output in enumerate(outputs):
+    print(f"{i+1}: {tokenizer.decode(output, skip_special_tokens=True)}")
+```
+
+## Preprocess text
+
+```python
+import re
+
+def normalize(s, truncate=100):
+    # Replace "\n" with "  "
+    s = s.replace("\n", "  ")
+    
+    # Keep only letters (including accented letters) and spaces
+    s = re.sub(r"[^a-zA-Zà-üÀ-Ü ]", "", s)
+    
+    # Split the string into words, truncate to the first 100 words, and join back into a string
+    words = s.split()
+    truncated = words[:truncate]
+    s = " ".join(truncated)
+    
+    # Remove additional spaces
+    s = re.sub(r"\s+", " ", s)
+    
+    return s
+
+
+
+def create_full_text(homepageText,metakeywords = "", title = "", meta = "", aboutText = "",  truncate_limit=100):
+    return (
+        "[METAKEYWORD] " + normalize(metakeywords, truncate=truncate_limit) +
+        " [TITLE] " + normalize(title, truncate=truncate_limit) +
+        " [META] " + normalize(meta, truncate=truncate_limit) +
+        " [ABOUT] " + normalize(aboutText, truncate=truncate_limit) +
+        # Assuming we want to normalize homepageText with a much higher limit or no truncation
+        " [HOME] " + normalize(homepageText, truncate=truncate_limit)
+    ).strip()
+
+# Sample raw inputs
+metakeywords = "Green Energy, Sustainability"
+meta = "Exploring innovative solutions for a sustainable future."
+homepageText = "Welcome to our green energy platform where we share insights and innovations..."
+aboutText = "We are committed to advancing green energy solutions through research and development."
+title = "Green Energy Innovations"
+
+# Applying your preprocessing steps
+full_text = create_full_text(metakeywords, title, meta, aboutText, homepageText)
+
+print(full_text)
+```
+
+## Simple usage
+
+```python
+from transformers import pipeline
+import re
+
+model_name_or_path = "Rel8ed/cleantech-cls"
+
+classifier = pipeline('text-classification', model=model_name_or_path)
+
+def normalize(s, truncate=100):
+    s = s.replace("\n", "  ")
+    s = re.sub(r"[^a-zA-Zà-üÀ-Ü ]", "", s)
+    words = s.split()
+    truncated = words[:truncate]
+    s = " ".join(truncated)
+    s = re.sub(r"\s+", " ", s)
+    return s
+
+
+def create_full_text(homepageText,metakeywords = "", title = "", meta = "", aboutText = "",  truncate_limit=100):
+    return (
+        "[METAKEYWORD] " + normalize(metakeywords, truncate=truncate_limit) +
+        " [TITLE] " + normalize(title, truncate=truncate_limit) +
+        " [META] " + normalize(meta, truncate=truncate_limit) +
+        " [ABOUT] " + normalize(aboutText, truncate=truncate_limit) +
+        # Assuming we want to normalize homepageText with a much higher limit or no truncation
+        " [HOME] " + normalize(homepageText, truncate=truncate_limit)
+    ).strip()
+
+text = "Welcome to our green energy platform where we share insights and innovations"
+
+predictions = classifier(create_full_text(text))
+
+```