Upload 4 files

README.md

@@ -1,12 +1,14 @@
 ---
-title: Chatbot 1
-emoji: 📉
-colorFrom: purple
-colorTo: pink
+title: 프롬프트용 챗봇
+emoji: 🫠💬
+colorFrom: yellow
+colorTo: purple
 sdk: gradio
 sdk_version: 4.42.0
 app_file: app.py
-pinned: false
+pinned: true
+license: apache-2.0
+short_description: Prompt_Chat
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

app.py

@@ -0,0 +1,114 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+import os
+
+MODELS = {
+    "Zephyr 7B Beta": "HuggingFaceH4/zephyr-7b-beta",
+    "DeepSeek Coder V2": "deepseek-ai/DeepSeek-Coder-V2-Instruct",
+    "Meta Llama 3.1 8B": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+    "Mixtral 8x7B": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+    "Cohere Command R+": "CohereForAI/c4ai-command-r-plus",
+}
+
+def get_client(model_name):
+    model_id = MODELS[model_name]
+    hf_token = os.getenv("HF_TOKEN")
+    if not hf_token:
+        raise ValueError("HF_TOKEN environment variable is required")
+    return InferenceClient(model_id, token=hf_token)
+
+def respond(
+    message,
+    chat_history,
+    model_name,
+    max_tokens,
+    temperature,
+    top_p,
+    system_message,
+):
+    try:
+        client = get_client(model_name)
+    except ValueError as e:
+        chat_history.append((message, str(e)))
+        return chat_history
+
+    messages = [{"role": "system", "content": system_message}]
+    for human, assistant in chat_history:
+        messages.append({"role": "user", "content": human})
+        messages.append({"role": "assistant", "content": assistant})
+    messages.append({"role": "user", "content": message})
+
+    try:
+        if "Cohere" in model_name:
+            # Cohere 모델을 위한 비스트리밍 처리
+            response = client.chat_completion(
+                messages,
+                max_tokens=max_tokens,
+                temperature=temperature,
+                top_p=top_p,
+            )
+            assistant_message = response.choices[0].message.content
+            chat_history.append((message, assistant_message))
+            yield chat_history
+        else:
+            # 다른 모델들을 위한 스트리밍 처리
+            stream = client.chat_completion(
+                messages,
+                max_tokens=max_tokens,
+                temperature=temperature,
+                top_p=top_p,
+                stream=True,
+            )
+            partial_message = ""
+            for response in stream:
+                if response.choices[0].delta.content is not None:
+                    partial_message += response.choices[0].delta.content
+                    if len(chat_history) > 0 and chat_history[-1][0] == message:
+                        chat_history[-1] = (message, partial_message)
+                    else:
+                        chat_history.append((message, partial_message))
+                    yield chat_history
+    except Exception as e:
+        error_message = f"An error occurred: {str(e)}"
+        chat_history.append((message, error_message))
+        yield chat_history
+
+def clear_conversation():
+    return []
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Prompting AI Chatbot")
+    gr.Markdown("언어모델별 프롬프트 테스트 챗봇입니다.")
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            model_name = gr.Radio(
+                choices=list(MODELS.keys()),
+                label="Language Model",
+                value="Zephyr 7B Beta"
+            )
+            max_tokens = gr.Slider(minimum=0, maximum=2000, value=500, step=100, label="Max Tokens")
+            temperature = gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.05, label="Temperature")
+            top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p")
+            system_message = gr.Textbox(
+                value="""반드시 한글로 답변할 것.
+너는 최고의 비서이다.
+내가 요구하는것들을 최대한 자세하고 정확하게 답변하라.
+""",
+                label="System Message",
+                lines=3
+            )
+
+        with gr.Column(scale=2):
+            chatbot = gr.Chatbot()
+            msg = gr.Textbox(label="메세지를 입력하세요")
+            with gr.Row():
+                submit_button = gr.Button("전송")
+                clear_button = gr.Button("대화 내역 지우기")
+
+    msg.submit(respond, [msg, chatbot, model_name, max_tokens, temperature, top_p, system_message], chatbot)
+    submit_button.click(respond, [msg, chatbot, model_name, max_tokens, temperature, top_p, system_message], chatbot)
+    clear_button.click(clear_conversation, outputs=chatbot, queue=False)
+
+if __name__ == "__main__":
+    demo.launch()

gitattributes

@@ -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 +1,3 @@
+gradio
+huggingface_hub
+minijinja