Add all files

README.md

@@ -1,13 +1,50 @@
----
-title: Shakespeare GPT
-emoji: 👀
-colorFrom: pink
-colorTo: indigo
-sdk: gradio
-sdk_version: 5.10.0
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+# Shakespeare-GPT Space
+
+This space is a demonstration of a fine-tuned GPT-2 model trained on Shakespearean text, offering users the ability to generate text inspired by the Bard's style.
+
+## Features
+
+- **Generate Text**: Input a prompt and let the model generate Shakespearean-style text.
+- **Customizable Settings**: Adjust parameters like maximum length, temperature, and sampling method (e.g., top-p, top-k) for fine-tuned control over the output.
+- **Gradio Interface**: User-friendly interface powered by Gradio for seamless interaction.
+
+## How to Use
+
+1. Enter a prompt in the input box.
+2. Adjust settings (optional) for generation control.
+3. Click the "Generate" button and wait for your text to appear.
+
+## Example Prompts
+
+- "Oh noble knight, what hast thou seen?"
+- "To love or not to love, that is the query."
+- "The moon shines brightly upon the silent woods."
+
+## Technologies
+
+- **Model**: GPT-2 fine-tuned on Shakespearean text.
+- **Framework**: Gradio for the web interface.
+- **Platform**: Hosted on Hugging Face Spaces.
+
+## Requirements
+
+This space uses the following dependencies (also listed in `requirements.txt`):
+
+```
+gradio
+transformers
+torch
+```
+
+## About the Model
+
+The model was fine-tuned using the tinyShakespeare dataset. Its outputs are influenced by the training data, generating text that resembles Shakespearean prose and verse.
+
+## Acknowledgments
+
+Special thanks to Hugging Face and Gradio for providing the tools to make this project possible.
+
+## License
+
+This project is under the apache-2.0 license.

app.py

@@ -0,0 +1,29 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the model and tokenizer
+model_name = "mstftmk/shakespeare-gpt2"  # Replace with your model's repo
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Define the generation function
+def generate_text(input_text, max_length, temperature):
+    inputs = tokenizer.encode(input_text, return_tensors="pt")
+    outputs = model.generate(inputs, max_length=max_length, temperature=temperature)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Create the Gradio interface
+interface = gr.Interface(
+    fn=generate_text,
+    inputs=[
+        gr.Textbox(lines=2, placeholder="Enter your prompt..."),
+        gr.Slider(50, 300, value=100, label="Max Length"),
+        gr.Slider(0.1, 1.0, value=0.7, label="Temperature"),
+    ],
+    outputs=gr.Textbox(),
+    title="Shakespeare GPT-2",
+    description="Generate text inspired by Shakespeare.",
+)
+
+# Launch the Gradio app
+interface.launch()

requirements.txt

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