Update app.py

app.py

@@ -4,12 +4,12 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
 # Load the model and config when the script starts
-config = PeftConfig.from_pretrained("PhantHive/llama-2-7b-momo")
-model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-7b-chat-hf")
-model = PeftModel.from_pretrained(model, "PhantHive/llama-2-7b-momo")
+config = PeftConfig.from_pretrained("Phearion/bigbrain-v0.0.1")
+model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
+model = PeftModel.from_pretrained(model, "Phearion/bigbrain-v0.0.1")
 
 # Load the tokenizer
-tokenizer = AutoTokenizer.from_pretrained("NousResearch/Llama-2-7b-chat-hf")
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
 
 
 def greet(text):
@@ -17,9 +17,10 @@ def greet(text):
 
     # Use torch.no_grad to disable gradient calculation
     with torch.no_grad():
-        output_tokens = model.generate(**batch, do_sample=True, max_new_tokens=50)
+        output_tokens = model.generate(**batch, do_sample=True, max_new_tokens=20)
 
-    return tokenizer.decode(output_tokens[0], skip_special_tokens=True)
+    return tokenizer.decode
+(output_tokens[0], skip_special_tokens=True)
 
 
 iface = gr.Interface(fn=greet, inputs="text", outputs="text")