Update app.py

app.py

@@ -1,63 +1,39 @@
 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()
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load model and tokenizer
+model_name = "skkjodhpur/Gemma-Code-Instruct-Finetune-by-skk"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
+
+# Move model to GPU if available
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = model.to(device)
+
+def generate_text(prompt):
+    # Tokenize input
+    input_ids = tokenizer.encode(f"<s>[INST] {prompt} [/INST]", return_tensors="pt").to(device)
+
+    # Generate text
+    with torch.no_grad():
+        output = model.generate(
+            input_ids,
+            max_length=200,
+            num_return_sequences=1,
+            do_sample=True,
+            temperature=0.7,
+        )
+
+    # Decode and return the generated text
+    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    return generated_text
+
+# Gradio interface
+def chatbot_response(user_input):
+    return generate_text(user_input)
+
+iface = gr.Interface(fn=chatbot_response, inputs="text", outputs="text", title="Code Chatbot",
+                     description="Ask me to write code snippets or explain programming concepts!")
+
+iface.launch()