Update app.py

app.py

@@ -1,10 +1,25 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
+os.system('pip install peft transformers')
 
+
+import spaces
+from transformers import GemmaTokenizer, AutoModelForCausalLM
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from threading import Thread
+HF_TOKEN = os.environ.get("HF_TOKEN", None)
 """
 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 tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("LLMproj1/mypersona-llama3-8b")
+model = AutoModelForCausalLM.from_pretrained("LLMproj1/mypersona-llama3-8b", device_map="auto")
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
 
 
 def respond(