Update app.py

app.py

@@ -1,20 +1,14 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel, PeftConfig
 
-"""
-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")
+# Load the PEFT configuration, base model, and tokenizer
+config = PeftConfig.from_pretrained("SahilCarterr/Llama-2-7B-Chat-PEFT")
+base_model = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7b-Chat-GPTQ", device_map='auto')
+model = PeftModel.from_pretrained(base_model, "SahilCarterr/Llama-2-7B-Chat-PEFT")
+tokenizer = AutoTokenizer.from_pretrained("SahilCarterr/Llama-2-7B-Chat-PEFT")
 
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -24,24 +18,15 @@ def respond(
             messages.append({"role": "assistant", "content": val[1]})
 
     messages.append({"role": "user", "content": message})
+    
+    # Encode the input
+    inputs = tokenizer(message, return_tensors="pt").input_ids.to('cuda')
+    # Generate the response using the model
+    outputs = model.generate(inputs, max_new_tokens=max_tokens, do_sample=True, temperature=temperature, top_p=top_p)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-    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
+    yield response
 
-        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=[
@@ -58,6 +43,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()