new

app.py

@@ -1,64 +1,108 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+from transformers import AutoModel, AutoTokenizer
+from datasets import load_dataset
+import torch
+
+# 加载预训练模型和分词器
+MODEL_NAME = "bert-base-chinese"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModel.from_pretrained(MODEL_NAME)
+
+# 加载tnews数据集
+dataset = load_dataset("clue", "tnews")
+
+# 数据预处理函数
+def preprocess_text(text):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=128)
+    return inputs
+
+# 特征提取函数
+def extract_features(text):
+    inputs = preprocess_text(text)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    # 使用[CLS] token的表示作为特征
+    cls_embedding = outputs.last_hidden_state[:, 0, :].squeeze().numpy()
+    return cls_embedding
 
+# Gradio接口
+def predict(text):
+    features = extract_features(text)
+    return f"特征维度: {features.shape}\n特征向量（部分展示）: {features[:10]}"
 
+# 定义界面
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Textbox(lines=2, placeholder="输入中文文本..."),
+    outputs="text",
+    title="中文特征提取",
+    description="基于BERT的中文文本特征提取，使用tnews数据集进行微调。",
+)
+
+# 运行Gradio应用
 if __name__ == "__main__":
     demo.launch()
+# import gradio as gr
+# from huggingface_hub import InferenceClient
+
+# """
+# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+# """
+# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+
+# def respond(
+#     message,
+#     history: list[tuple[str, str]],
+#     system_message,
+#     max_tokens,
+#     temperature,
+#     top_p,
+# ):
+#     messages = [{"role": "system", "content": system_message}]
+
+#     for val in history:
+#         if val[0]:
+#             messages.append({"role": "user", "content": val[0]})
+#         if val[1]:
+#             messages.append({"role": "assistant", "content": val[1]})
+
+#     messages.append({"role": "user", "content": message})
+
+#     response = ""
+
+#     for message in client.chat_completion(
+#         messages,
+#         max_tokens=max_tokens,
+#         stream=True,
+#         temperature=temperature,
+#         top_p=top_p,
+#     ):
+#         token = message.choices[0].delta.content
+
+#         response += token
+#         yield response
+
+
+# """
+# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+# """
+# demo = gr.ChatInterface(
+#     respond,
+#     additional_inputs=[
+#         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+#         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+#         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+#         gr.Slider(
+#             minimum=0.1,
+#             maximum=1.0,
+#             value=0.95,
+#             step=0.05,
+#             label="Top-p (nucleus sampling)",
+#         ),
+#     ],
+# )
+
+
+# if __name__ == "__main__":
+#     demo.launch()

requirements.txt

@@ -1 +1,5 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+transformers
+datasets
+gradio
+torch