Update app.py

app.py

@@ -1,11 +1,14 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import os
 
-"""
-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")
+# Define the repository ID and access token
+repo_id = "Mikhil-jivus/Llama-32-3B-FineTuned"
+access_token = os.getenv('HF_TOKEN')
 
+# Load the tokenizer and model from the Hugging Face repository
+tokenizer = AutoTokenizer.from_pretrained(repo_id, use_auth_token=access_token)
+model = AutoModelForCausalLM.from_pretrained(repo_id, use_auth_token=access_token)
 
 def respond(
     message,
@@ -25,19 +28,24 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    # Tokenize the input messages
+    input_text = system_message + " ".join([f"{msg['role']}: {msg['content']}" for msg in messages])
+    input_ids = tokenizer.encode(input_text, return_tensors="pt")
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # Generate a response
+    chat_history_ids = model.generate(
+        input_ids,
+        max_length=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        pad_token_id=tokenizer.eos_token_id,
+        do_sample=True,
+    )
 
-        response += token
-        yield response
+    # Decode the response
+    response = tokenizer.decode(chat_history_ids[:, input_ids.shape[-1]:][0], skip_special_tokens=True)
+
+    yield response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -58,6 +66,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()