model updated model_id = "TheBloke/Mistral-7B-Instruct-v0.2-GGUF"

app.py

@@ -54,7 +54,7 @@ def initialize_agent(
     checkpointer = MemorySaver()
 
     # Load local Hugging Face model
-    hf_model_id = "mistralai/Mistral-7B-Instruct-v0.2"
+    hf_model_id = model_id = "TheBloke/Mistral-7B-Instruct-v0.2-GGUF"
     tokenizer = AutoTokenizer.from_pretrained(hf_model_id)
     raw_model = AutoModelForCausalLM.from_pretrained(hf_model_id, device_map="auto")
 
@@ -63,7 +63,7 @@ def initialize_agent(
         model=raw_model,
         tokenizer=tokenizer,
         max_new_tokens=512,
-        temperature=temperature,
+        temperature=temperature,`
         top_p=top_p,
         return_full_text=False,
     )