Update app.py

app.py

@@ -4,6 +4,9 @@ from transformers import AutoModel, AutoTokenizer
 import streamlit as st
 from streamlit_chat import message
 from fastllm_pytools import llm
+from huggingface_hub import snapshot_download,hf_hub_download
+
+hf_hub_download(repo_id="huangyuyang/chatglm2-6b-int4.flm",local_dir="./", filename="chatglm2-6b-int4.flm")
 
 st.set_page_config(
     page_title="ChatGLM2-6b 演示",
@@ -15,9 +18,7 @@ st.set_page_config(
 @st.cache_resource
 def get_model():
     tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True)
-    model = AutoModel.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True).float()
-
-    model = llm.from_hf(model, tokenizer, dtype = "int4")
+    model = llm.model(chatglm2-6b-int4.flm)
     #model = model.eval()
     return tokenizer, model