done

app.py

@@ -8,17 +8,19 @@ from llama_index.core.postprocessor import SimilarityPostprocessor
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 from llama_index.core import Document
 import re
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import LlamaTokenizer, LlamaForCausalLM
+
 
 print("started...........................................................")
-model_id ="Dobby091/KOKO"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
+model_path = "/mnt/data1/backup/viswaz/Project_K/huggingface_cache/Mistral-7B-Instruct-v0.2"
+tokenizer = LlamaTokenizer.from_pretrained(model_path)
+model = LlamaForCausalLM.from_pretrained(
+    model_path,
     device_map="auto",
-    cache_dir = "/mnt/data1/backup/viswaz/Project_K/huggingface_cache/",
+    cache_dir="/mnt/data1/backup/viswaz/Project_K/huggingface_cache/",
 )
 
+
 print("stage1         ------------------             completed")
 
 def generate_response(prompt, model):