Update app.py

app.py

@@ -1,64 +1,38 @@
 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)",
-        ),
-    ],
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the fine-tuned model and tokenizer
+model = AutoModelForCausalLM.from_pretrained("PierreJousselin/lora_model")
+tokenizer = AutoTokenizer.from_pretrained("PierreJousselin/lora_model")
+
+# Define the text generation function
+def generate_text(prompt):
+    # Encode the input prompt
+    input_ids = tokenizer.encode(prompt, return_tensors="pt")
+    
+    # Generate text using the model
+    generated_ids = model.generate(
+        input_ids,
+        max_length=150,  # Maximum length of the generated text
+        num_return_sequences=1,  # Number of sequences to generate
+        temperature=0.7,  # Sampling temperature (controls randomness)
+        top_p=0.9,  # Nucleus sampling (controls diversity)
+        top_k=50,  # Top-k sampling (limits the number of next word candidates)
+        no_repeat_ngram_size=2,  # Avoid repeating n-grams
+    )
+    
+    # Decode the generated text
+    generated_text = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
+    return generated_text
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=generate_text,  # The function to call when the user provides input
+    inputs=gr.Textbox(lines=2, placeholder="Enter your prompt here..."),  # Input box
+    outputs=gr.Textbox(),  # Output box to display the generated text
+    title="Lora Fine-Tuned Language Model",  # Interface title
+    description="This is a Gradio interface for the Lora fine-tuned language model. Enter a prompt to generate text.",  # Description
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the interface
+iface.launch()