Update app.py

app.py

@@ -1,48 +1,24 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import os
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load your model and tokenizer
+model_name = "rshaikh22/coachcarellm"  # Replace with your actual model repo
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Move model to appropriate device
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+def respond(message, history):
+    input_text = message
+    inputs = tokenizer.encode(input_text + tokenizer.eos_token, return_tensors="pt").to(device)
+    outputs = model.generate(inputs, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
 
-"""
-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=[
@@ -59,6 +35,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()