Upload 4 files

README.md

@@ -1,13 +1,13 @@
 ---
-title: YgIV
-emoji: 📈
-colorFrom: pink
-colorTo: gray
+title: Chatglm2 6b Int4
+emoji: 🚀
+colorFrom: green
+colorTo: red
 sdk: streamlit
-sdk_version: 1.27.2
+sdk_version: 1.21.0
 app_file: app.py
 pinned: false
-license: apache-2.0
+duplicated_from: Cran-May/yugang-chatglm2-6b-int4
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,74 @@
+# https://github.com/THUDM/ChatGLM2-6B/blob/main/web_demo2.py
+
+from transformers import AutoModel, AutoTokenizer
+import streamlit as st
+from streamlit_chat import message
+
+
+st.set_page_config(
+    page_title="ChatGLM2-6b 演示",
+    page_icon=":robot:",
+    layout='wide'
+)
+
+
+@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 = model.eval()
+    return tokenizer, model
+
+
+MAX_TURNS = 20
+MAX_BOXES = MAX_TURNS * 2
+
+
+def predict(input, max_length, top_p, temperature, history=None):
+    tokenizer, model = get_model()
+    if history is None:
+        history = []
+
+    with container:
+        if len(history) > 0:
+            if len(history)>MAX_BOXES:
+                history = history[-MAX_TURNS:]
+            for i, (query, response) in enumerate(history):
+                message(query, avatar_style="big-smile", key=str(i) + "_user")
+                message(response, avatar_style="bottts", key=str(i))
+
+        message(input, avatar_style="big-smile", key=str(len(history)) + "_user")
+        st.write("AI正在回复:")
+        with st.empty():
+            for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
+                                               temperature=temperature):
+                query, response = history[-1]
+                st.write(response)
+
+    return history
+
+
+container = st.container()
+
+# create a prompt text for the text generation
+prompt_text = st.text_area(label="用户命令输入",
+            height = 100,
+            placeholder="请在这儿输入您的命令")
+
+max_length = st.sidebar.slider(
+    'max_length', 0, 32768, 8192, step=1
+)
+top_p = st.sidebar.slider(
+    'top_p', 0.0, 1.0, 0.8, step=0.01
+)
+temperature = st.sidebar.slider(
+    'temperature', 0.0, 1.0, 0.95, step=0.01
+)
+
+if 'state' not in st.session_state:
+    st.session_state['state'] = []
+
+if st.button("发送", key="predict"):
+    with st.spinner("AI正在思考，请稍等........"):
+        # text generation
+        st.session_state["state"] = predict(prompt_text, max_length, top_p, temperature, st.session_state["state"])

gitattributes.txt

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,4 @@
+torch>=2.0
+transformers==4.30.2
+sentencepiece
+streamlit_chat