Update app.py

app.py

@@ -47,7 +47,12 @@ if not torch.cuda.is_available():
 # if torch.cuda.is_available():
 model_id = "DAMO-NLP-SG/CLEX-7b-Chat-16K"
 from transformers import AutoModelForCausalLM
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True)
+from modeling_llama import LlamaForCausalLM
+# from configuration_clex import CLEXLlamaConfig
+# config = CLEXLlamaConfig.from_pretrained(
+#         model_id
+#     )
+model = LlamaForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
 tokenizer.use_default_system_prompt = False