Update transformers_inference_example.py

transformers_inference_example.py

@@ -3,11 +3,11 @@
 
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
-from transformers import LlamaTokenizer, LlamaForCausalLM, MistralForCausalLM
+from transformers import LlamaTokenizer, MixtralForCausalLM
 import bitsandbytes, flash_attn
 
 tokenizer = LlamaTokenizer.from_pretrained('NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO', trust_remote_code=True)
-model = MistralForCausalLM.from_pretrained(
+model = MixtralForCausalLM.from_pretrained(
     "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
     torch_dtype=torch.float16,
     device_map="auto",