changed model to saiga_llama3_8b

app.py

@@ -4,8 +4,8 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria,
 from threading import Thread
 
 
-tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")
-model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")  #, torch_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained("IlyaGusev/saiga_llama3_8b")
+model = AutoModelForCausalLM.from_pretrained("IlyaGusev/saiga_llama3_8b")  #, torch_dtype=torch.float16)
 model = model  #.to('cuda')