Update app.py

app.py

@@ -2,23 +2,29 @@ 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
+"""
+
+import os
+client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta", token=os.getenv("HUGGINGFACEHUB_API_TOKEN"))
+
+
 def respond(
     message,
-    history: list[dict[str, str]],
+    history: list[tuple[str, str]],
     system_message,
     max_tokens,
     temperature,
     top_p,
-    hf_token: gr.OAuthToken,
 ):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
     messages = [{"role": "system", "content": system_message}]
 
-    messages.extend(history)
+    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})
 
@@ -31,10 +37,7 @@ def respond(
         temperature=temperature,
         top_p=top_p,
     ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+        token = message.choices[0].delta.content
 
         response += token
         yield response
@@ -43,9 +46,8 @@ def respond(
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
-chatbot = gr.ChatInterface(
+demo = gr.ChatInterface(
     respond,
-    type="messages",
     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"),
@@ -60,11 +62,37 @@ chatbot = gr.ChatInterface(
     ],
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
 
 if __name__ == "__main__":
     demo.launch()
+
+import os
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+# Load Hugging Face API token securely
+api_token = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+
+if not api_token:
+    raise ValueError("❌ ERROR: Hugging Face API token is not set. Please set it as an environment variable.")
+
+# Define model names
+base_model_name = "unsloth/qwen2.5-math-7b-bnb-4bit"
+peft_model_name = "Hrushi02/Root_Math"
+
+# Load base model with authentication
+base_model = AutoModelForCausalLM.from_pretrained(
+    base_model_name,
+    torch_dtype=torch.float16,
+    device_map="auto",
+    use_auth_token=api_token  # ✅ Correct
+)
+
+
+# Load fine-tuned model
+model = PeftModel.from_pretrained(base_model, peft_model_name, token=api_token)
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(base_model_name, token=api_token)
+