Update app.py

app.py

@@ -1,143 +1,112 @@
 import numpy as np
 import streamlit as st
-import os
-import sys
-
-
-
-# Create supported models
-model_links = {
-    "Mistral-Nemo-Base-2407": "joermd/speedy-llama2",
-}
-
-#Random dog images for error message
-random_dog = ["0f476473-2d8b-415e-b944-483768418a95.jpg",
-              "1bd75c81-f1d7-4e55-9310-a27595fa8762.jpg",
-              "526590d2-8817-4ff0-8c62-fdcba5306d02.jpg",
-              "1326984c-39b0-492c-a773-f120d747a7e2.jpg",
-              "42a98d03-5ed7-4b3b-af89-7c4876cb14c3.jpg",
-              "8b3317ed-2083-42ac-a575-7ae45f9fdc0d.jpg",
-              "ee17f54a-83ac-44a3-8a35-e89ff7153fb4.jpg",
-              "027eef85-ccc1-4a66-8967-5d74f34c8bb4.jpg",
-              "08f5398d-7f89-47da-a5cd-1ed74967dc1f.jpg",
-              "0fd781ff-ec46-4bdc-a4e8-24f18bf07def.jpg",
-              "0fb4aeee-f949-4c7b-a6d8-05bf0736bdd1.jpg",
-              "6edac66e-c0de-4e69-a9d6-b2e6f6f9001b.jpg",
-              "bfb9e165-c643-4993-9b3a-7e73571672a6.jpg"]
-
-
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# التحقق من توفر GPU
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+@st.cache_resource
+def load_model():
+    """
+    تحميل النموذج والمُرمِّز مع التخزين المؤقت
+    """
+    model = AutoModelForCausalLM.from_pretrained(
+        "joermd/speedy-llama2",
+        torch_dtype=torch.float16,
+        device_map=device
+    )
+    tokenizer = AutoTokenizer.from_pretrained("joermd/speedy-llama2")
+    return model, tokenizer
+
+# الصور العشوائية للكلاب عند حدوث خطأ
+random_dog = [
+    "0f476473-2d8b-415e-b944-483768418a95.jpg",
+    "1bd75c81-f1d7-4e55-9310-a27595fa8762.jpg",
+    "526590d2-8817-4ff0-8c62-fdcba5306d02.jpg",
+    "1326984c-39b0-492c-a773-f120d747a7e2.jpg",
+    "42a98d03-5ed7-4b3b-af89-7c4376cb14c3.jpg"
+]
 
 def reset_conversation():
     '''
-    Resets Conversation
+    إعادة تعيين المحادثة
     '''
     st.session_state.conversation = []
     st.session_state.messages = []
     return None
-    
-
-
-
-# Define the available models
-models =[key for key in model_links.keys()]
-
-# Create the sidebar with the dropdown for model selection
-selected_model = st.sidebar.selectbox("Select Model", models)
-
-# Create a temperature slider
-temp_values = st.sidebar.slider('Select a temperature value', 0.0, 1.0, (0.5))
-
-# Create a max_token slider
-max_token_value = st.sidebar.slider('Select a max_token value', 1000, 9000, (5000))
-
-#Add reset button to clear conversation
-st.sidebar.button('Reset Chat', on_click=reset_conversation) #Reset button
-
-
-# Create model description
-st.sidebar.write(f"You're now chatting with **{selected_model}**")
-st.sidebar.markdown("*Generated content may be inaccurate or false.*")
-# st.sidebar.markdown("\n[TypeGPT](https://typegpt.net).")
-
-
-
-
-if "prev_option" not in st.session_state:
-    st.session_state.prev_option = selected_model
 
-if st.session_state.prev_option != selected_model:
-    st.session_state.messages = []
-    # st.write(f"Changed to {selected_model}")
-    st.session_state.prev_option = selected_model
-    reset_conversation()
-
-
-
-#Pull in the model we want to use
-repo_id = model_links[selected_model]
-
-
-st.subheader(f'{selected_model}')
-# # st.title(f'ChatBot Using {selected_model}')
-
-# Set a default model
-if selected_model not in st.session_state:
-    st.session_state[selected_model] = model_links[selected_model] 
-
-# Initialize chat history
+def generate_response(prompt, temperature, max_length):
+    """
+    توليد استجابة من النموذج
+    """
+    try:
+        inputs = tokenizer.encode(prompt, return_tensors="pt").to(device)
+        
+        with torch.no_grad():
+            outputs = model.generate(
+                inputs,
+                max_length=max_length,
+                temperature=temperature,
+                do_sample=True,
+                pad_token_id=tokenizer.eos_token_id
+            )
+        
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        return response
+    except Exception as e:
+        return str(e)
+
+# تحميل النموذج والمُرمِّز
+try:
+    with st.spinner('جاري تحميل النموذج... قد يستغرق هذا بضع دقائق...'):
+        model, tokenizer = load_model()
+except Exception as e:
+    st.error(f"حدث خطأ أثناء تحميل النموذج: {str(e)}")
+    st.stop()
+
+# إعداد واجهة Streamlit
+st.subheader('Mistral Chat')
+
+# إضافة أزرار التحكم في الشريط الجانبي
+temp_values = st.sidebar.slider('اختر قيمة درجة الحرارة', 0.0, 1.0, 0.5)
+max_token_value = st.sidebar.slider('اختر الحد الأقصى للرموز', 100, 2000, 500)
+st.sidebar.button('إعادة تعيين المحادثة', on_click=reset_conversation)
+
+# تهيئة سجل المحادثة
 if "messages" not in st.session_state:
     st.session_state.messages = []
 
-
-# Display chat messages from history on app rerun
+# عرض رسائل المحادثة السابقة
 for message in st.session_state.messages:
     with st.chat_message(message["role"]):
         st.markdown(message["content"])
 
-
-
-# Accept user input
-if prompt := st.chat_input(f"Hi I'm {selected_model}, ask me a question"):
-    # Display user message in chat message container
+# معالجة إدخال المستخدم
+if prompt := st.chat_input("اسألني سؤالاً"):
+    # عرض رسالة المستخدم
     with st.chat_message("user"):
         st.markdown(prompt)
-    # Add user message to chat history
     st.session_state.messages.append({"role": "user", "content": prompt})
     
-
-    # Display assistant response in chat message container
+    # عرض رد المساعد
     with st.chat_message("assistant"):
         try:
-            stream = client.chat.completions.create(
-                model=model_links[selected_model],
-                messages=[
-                    {"role": m["role"], "content": m["content"]}
-                    for m in st.session_state.messages
-                ],
-                temperature=temp_values,#0.5,
-                stream=True,
-                max_tokens=max_token_value,
-            )
-    
-            response = st.write_stream(stream)
+            # توليد الرد
+            with st.spinner('جاري التفكير...'):
+                response = generate_response(
+                    prompt,
+                    temperature=temp_values,
+                    max_length=max_token_value
+                )
+            st.write(response)
 
         except Exception as e:
-            # st.empty()
-            response = "😵‍💫 Looks like someone unplugged something!\
-                    \n Either the model space is being updated or something is down.\
-                    \n\
-                    \n Try again later. \
-                    \n\
-                    \n Here's a random pic of a 🐶:"
+            response = "😵‍💫 يبدو أن هناك خطأ ما!\n حاول مرة أخرى لاحقاً.\n\n إليك صورة عشوائية لكلب 🐶:"
             st.write(response)
-            random_dog_pick = 'https://random.dog/'+ random_dog[np.random.randint(len(random_dog))]
+            random_dog_pick = 'https://random.dog/' + random_dog[np.random.randint(len(random_dog))]
             st.image(random_dog_pick)
-            st.write("This was the error message:")
+            st.write("رسالة الخطأ:")
             st.write(e)
 
-
-
-
-            
-
-    st.session_state.messages.append({"role": "assistant", "content": response})
+        st.session_state.messages.append({"role": "assistant", "content": response})