add application

README.md

@@ -8,6 +8,9 @@ sdk_version: 5.49.1
 app_file: app.py
 pinned: false
 short_description: Llama3-TAIDE-LX-8B-Chat-Alpha1 demo
+models:
+- taide/Llama3-TAIDE-LX-8B-Chat-Alpha1
+- taide/Llama3-TAIDE-LX-8B-Chat-Alpha1-GGUF
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,100 @@
+import gradio as gr
+import os
+import litellm
+
+DESCRIPTION = '''
+<div>
+<h1 style="text-align: center;">TAIDE/Llama3-TAIDE-LX-8B-Chat-Alpha1</h1>
+<p>This Space demonstrates the instruction-tuned model <a href="https://huggingface.co/taide/Llama3-TAIDE-LX-8B-Chat-Alpha1"><b>Llama3-TAIDE-LX-8B-Chat-Alpha1</b></a>. Llama3-TAIDE-LX-8B-Chat-Alpha1 is the new open LLM and comes in one sizes: 8b. Feel free to play with it, or duplicate to run privately!</p>
+</div>
+'''
+
+LICENSE = """
+<p/>
+---
+Built with Llama3-TAIDE-LX-8B-Chat-Alpha1
+"""
+
+css = """
+h1 {
+  text-align: center;
+  display: block;
+}
+#duplicate-button {
+  margin: auto;
+  color: white;
+  background: #1565c0;
+  border-radius: 100vh;
+}
+"""
+
+
+def chat(message: str,
+              history: list,
+              temperature: float,
+              max_new_tokens: int
+             ) -> str:
+    """
+    Generate a streaming response using the llama3-8b model.
+    """
+    try:
+        messages = []
+        for user, assistant in history:
+            messages.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
+        messages.append({"role": "user", "content": message})
+
+        response = litellm.completion(
+            model="openai/Llama3-TAIDE-LX-8B-Chat-Alpha1", # tells litellm to call the model via the Responses API
+            messages=messages,
+            max_completion_tokens=max_new_tokens,
+            temperature=temperature,
+            stream=True,
+
+        )
+        output = []
+        for part in response:
+            content = part.choices[0].delta.content or ""
+            output.append(content)
+            yield "".join(output)
+    except Exception as e:
+        yield f"生成過程中發生錯誤: {str(e)}"
+
+
+# Gradio block
+chatbot = gr.Chatbot(height=450, label='Gradio ChatInterface')
+
+with gr.Blocks(fill_height=True, css=css) as demo:
+
+    gr.Markdown(DESCRIPTION)
+    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
+    gr.ChatInterface(
+        fn=chat,
+        chatbot=chatbot,
+        fill_height=True,
+        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
+        additional_inputs=[
+            gr.Slider(minimum=0,
+                      maximum=1,
+                      step=0.1,
+                      value=0.95,
+                      label="Temperature",
+                      render=False),
+            gr.Slider(minimum=128,
+                      maximum=131584,
+                      step=1,
+                      value=512,
+                      label="Max new tokens",
+                      render=False),
+        ],
+        examples=[
+            ['請以以下內容為基礎，寫一篇文章：撰寫一篇作文，題目為《一張舊照片》，內容要求為：選擇一張令你印象深刻的照片，說明令你印象深刻的原因，並描述照片中的影像及背後的故事。記錄成長的過程、與他人的情景、環境變遷和美麗的景色。'],
+            ['請以品牌經理的身份，給廣告公司的創意總監寫一封信，提出對於新產品廣告宣傳活動的創意建議。'],
+            ['以下提供英文內容，請幫我翻譯成中文。Dongshan coffee is famous for its unique position, and the constant refinement of production methods. The flavor is admired by many caffeine afficionados.'],
+        ],
+        cache_examples=False,
+    )
+
+    gr.Markdown(LICENSE)
+
+if __name__ == "__main__":
+    demo.launch(server_name='0.0.0.0')

requirements.txt

@@ -0,0 +1,3 @@
+spaces
+gradio
+litellm