Update app.py

app.py

@@ -1,63 +1,45 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import re
+from transformers import pipeline
+
+# Function to clean and truncate the generated text after encountering unwanted content
+def clean_and_truncate_text(text):
+    # Remove any special tokens like [INST], [/INST], etc.
+    cleaned_text = re.sub(r"\[.*?\]", "", text)  # Remove square-bracket content
+    cleaned_text = cleaned_text.replace("</s>", "")  # Remove any leftover closing tag
+    cleaned_text = cleaned_text.strip()  # Remove leading/trailing whitespace
+
+    # Split the text and only keep the part before repetitive content or newlines
+    truncated_text = cleaned_text.split('\n')[0]  # Split by newline and take the first line
+    truncated_text = truncated_text.split('----')[0]  # Stop at the first '----' if it appears
+    return truncated_text.strip()  # Return cleaned and truncated text
+
+# Function to generate the model's response and print only the question and the first valid answer
+def chat_with_model(question):
+    # Format the question for the model
+    user_prompt = f"<s>[INST] {question} [/INST]"
+
+    # Initialize the text generation pipeline
+    text_generation_pipeline = pipeline(task="text-generation", model=llama_model, tokenizer=llama_tokenizer, max_length=100)
+
+    # Generate the answer from the model
+    model_answer = text_generation_pipeline(user_prompt)
+    generated_answer = model_answer[0]['generated_text']
+
+    # Clean and truncate the generated answer
+    cleaned_generated_answer = clean_and_truncate_text(generated_answer)
+
+    
+
+    return cleaned_generated_answer
+    
+# Create Gradio interface
+iface = gr.Interface(
+    fn=generate_answer,
+    inputs="text",
+    outputs="text",
+    title="Amharic Question-Answer Model",
+    description="Ask a question and get an answer based on the fine-tuned LLaMA model."
+    )
+
+# Launch the Gradio interface
+iface.launch()