Update getans.py

getans.py

@@ -1,15 +1,9 @@
-from mmap import mmap
-
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
-from huggingface_hub import login
-token1="hf_"
-token2="vWSzjVPShXPbgmylDJduWwHinTfHNqZVpj"
-login(token=token1+token2,add_to_git_credential=True)
+
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-mm="finetuning/output/pytorch_model.bin"
-tokenizer = AutoTokenizer.from_pretrained(mm)
-model = AutoModelForCausalLM.from_pretrained(mm)
+tokenizer = AutoTokenizer.from_pretrained("georgesung/llama2_7b_chat_uncensored")
+model = AutoModelForCausalLM.from_pretrained("georgesung/llama2_7b_chat_uncensored")
 
 def get_response(prompt, max_new_tokens=50):
     inputs = tokenizer(prompt, return_tensors="pt")