First

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/llm.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.8" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.8" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/llm.iml" filepath="$PROJECT_DIR$/.idea/llm.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

app.py

@@ -0,0 +1,86 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Initialize model and tokenizer
+model_name = "deepseek-ai/DeepSeek-V3-0324"
+
+print("Loading tokenizer...")
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+
+print("Loading model...")
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float16,  # Use float16 for efficiency
+    device_map="auto",  # Automatically determine device mapping
+    trust_remote_code=True
+)
+
+# Set model to evaluation mode
+model.eval()
+
+
+def generate_response(message, chat_history, system_prompt="You are a helpful AI assistant.", max_length=2048,
+                      temperature=0.7):
+    # Format the conversation
+    full_prompt = f"{system_prompt}\n\nUser: {message}\nAssistant:"
+
+    # Add chat history if it exists
+    if chat_history:
+        history_text = ""
+        for user_msg, assistant_msg in chat_history:
+            history_text += f"User: {user_msg}\nAssistant: {assistant_msg}\n"
+        full_prompt = f"{system_prompt}\n\n{history_text}User: {message}\nAssistant:"
+
+    # Tokenize input
+    inputs = tokenizer(full_prompt, return_tensors="pt").to(model.device)
+
+    # Generate response
+    with torch.no_grad():
+        outputs = model.generate(
+            inputs.input_ids,
+            max_length=max_length,
+            temperature=temperature,
+            do_sample=True,
+            pad_token_id=tokenizer.eos_token_id,
+            top_p=0.9,
+            repetition_penalty=1.1
+        )
+
+    # Decode and return the response
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    # Extract only the assistant's response
+    response = response.split("Assistant:")[-1].strip()
+
+    return response
+
+
+# Create the Gradio interface
+with gr.Blocks(css="footer {visibility: hidden}") as demo:
+    gr.Markdown("# DeepSeek V3 Chatbot")
+    gr.Markdown("Welcome! This is a chatbot powered by the DeepSeek-V3-0324 model.")
+
+    chatbot = gr.Chatbot(height=600)
+    msg = gr.Textbox(label="Type your message here...", placeholder="Hello! How can I help you today?")
+    clear = gr.Button("Clear Conversation")
+
+
+    def user(user_message, history):
+        return "", history + [[user_message, None]]
+
+
+    def bot(history):
+        user_message = history[-1][0]
+        bot_message = generate_response(user_message, history[:-1])
+        history[-1][1] = bot_message
+        return history
+
+
+    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
+        bot, chatbot, chatbot
+    )
+    clear.click(lambda: None, None, chatbot, queue=False)
+
+demo.queue()
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+gradio==4.19.2
+torch==2.2.0
+transformers==4.37.2
+accelerate==0.27.2