Initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+gradio_cached_examples

README.md

@@ -0,0 +1,12 @@
+---
+title: Dhivehi Text Generator (GPT-2, Wiki)
+emoji: 🌍
+colorFrom: blue
+colorTo: blue
+sdk: gradio
+sdk_version: 5.6.0
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,115 @@
+import spaces
+import gradio as gr
+from transformers import pipeline, GPT2TokenizerFast
+
+mode_id = "alakxender/dv-wiki-gpt2"
+tokenizer = GPT2TokenizerFast.from_pretrained(mode_id, model_max_length=128)
+
+generator = pipeline("text-generation", model=mode_id, tokenizer=tokenizer, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id)
+
+@spaces.GPU
+def generate_text(prompt, max_length, temperature):
+    try:
+        generated = generator(
+            prompt,
+            max_length=max_length,
+            temperature=temperature,
+            do_sample=True,
+            repetition_penalty=1.4
+        )
+        return generated[0]['generated_text']
+    except Exception as e:
+        return f"Something went wrong, try again. Error: {str(e)}"
+
+styles = """
+.thaana textarea {
+    font-size: 18px !important;
+    font-family: 'MV_Faseyha', 'Faruma', 'A_Faruma' !important;
+    line-height: 1.8 !important;
+}
+.textbox2 textarea {
+    display: none;
+}
+"""
+
+def create_interface(css=styles):
+    with gr.Blocks() as demo:
+        gr.Markdown("# Dhivehi Text Generator (GPT-2, Wiki)")
+        gr.Markdown(
+            "This is a GPT-2 model trained from Dhivehi text data from wikipedia"
+            "Enter some text and generate a new text, adjust the parameters to generate text."
+        )
+        gr.Markdown("""
+            **Parameters:**
+            
+            - **Temperature**: Controls the creativity of the output.
+              - Lower values (0.2) = More focused and predictable text
+              - Higher values (0.8) = More diverse and creative text
+            
+            - **Maximum Length**: Controls the length of generated text.
+              - Higher values generate longer, more detailed results
+              - Note: Longer texts take more time to generate
+        """)
+        
+        with gr.Row():
+            input_temperature = gr.Slider(
+                minimum=0.1,
+                maximum=1.0,
+                value=0.7,
+                step=0.1,
+                label="Temperature",
+            )
+            input_max_length = gr.Slider(
+                minimum=10,
+                maximum=128,
+                value=60,
+                step=1,
+                label="Maximum Length",
+            )
+        
+        with gr.Row():
+            with gr.Column(scale=1):
+                input_prompt = gr.Textbox(
+                    label="Enter dhivehi text prompt",
+                    placeholder="ދިވެހިން",
+                    lines=5,
+                    rtl=True,
+                    elem_classes="thaana"
+                )
+            
+            with gr.Column(scale=1):
+                output_text = gr.Textbox(
+                    label="Generated Text",
+                    lines=5,
+                    interactive=True,
+                    rtl=True,
+                    elem_classes="thaana"
+                )
+        
+        with gr.Row():
+            generate_btn = gr.Button("Generate", variant="primary")
+            clear_btn = gr.ClearButton([input_prompt, output_text])
+        
+        generate_btn.click(
+            fn=generate_text,
+            inputs=[input_prompt, input_max_length, input_temperature],
+            outputs=output_text
+        )
+        
+        gr.Examples(
+            examples=[
+                ["ދިވެހިރާއްޖެ"],
+                ["އެމެރިކާ އިންތިޚާބު"],
+                ["ސަލާމް"],
+                ["ދުނިޔޭގެ ސިއްޙަތު ޖަމްޢިއްޔާ"],
+                ["ޤަދީމީ ސަގާފަތް"],
+                ["ޑިމޮކްރަސީ"]
+            ],
+            inputs=input_prompt
+        )
+    
+    return demo            
+
+if __name__ == "__main__":
+    demo = create_interface()
+    demo.queue().launch(show_api=False)

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+tensorflow
+accelerate
+tf-keras