Duplicate from ZeroTwo3/flask_test

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Demo_flask
+emoji: 🏢
+colorFrom: purple
+colorTo: purple
+sdk: gradio
+sdk_version: 2.8.13
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: ZeroTwo3/flask_test
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -0,0 +1,86 @@
+import json
+import torch
+from flask import Flask, request, jsonify
+from transformers import GPT2Tokenizer, GPT2LMHeadModel, TextDataset, DataCollatorForLanguageModeling, Trainer
+import os
+
+app = Flask(__name__)
+
+# Load the fine-tuned model checkpoint if available; otherwise, load the pre-trained GPT-2 model
+if os.path.exists("fine_tuned_checkpoint"):
+    model = GPT2LMHeadModel.from_pretrained("fine_tuned_checkpoint")
+else:
+    model = GPT2LMHeadModel.from_pretrained("gpt2")
+
+tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
+
+# Function to fine-tune the model
+def fine_tune_model(chat_history):
+    # Prepare training data for fine-tuning
+    input_texts = [item["message"] for item in chat_history]
+    with open("train.txt", "w") as f:
+        f.write("\n".join(input_texts))
+    
+    # Load the dataset and create data collator
+    dataset = TextDataset(tokenizer=tokenizer, file_path="train.txt", block_size=128)
+    data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
+    
+    # Fine-tune the model
+    trainer = Trainer(model=model, data_collator=data_collator)
+    trainer.train("./training_directory")
+    
+    # Save the fine-tuned model
+    model.save_pretrained("fine_tuned_model")
+
+@app.route("/chat", methods=["POST"])
+def chat_with_model():
+    request_data = request.get_json()
+    user_input = request_data["user_input"]
+    chat_history = request_data.get("chat_history", [])
+
+    # Append user message to the chat history
+    chat_history.append({"role": "user", "message": user_input})
+
+    # Generate response
+    response = generate_response(user_input, chat_history)
+
+    # Append bot message to the chat history
+    chat_history.append({"role": "bot", "message": response})
+
+    return jsonify({"bot_response": response, "chat_history": chat_history})
+
+@app.route("/train", methods=["POST"])
+def train_model():
+    chat_history = request.json["data"]
+    
+    # Fine-tune the model with the provided data
+    fine_tune_model(chat_history)
+    
+    return "Model trained and updated successfully."
+
+def generate_response(user_input, chat_history):
+    # Set the maximum number of previous messages to consider
+    max_history = 3
+
+    # Use the last `max_history` messages from the chat history
+    inputs = [item["message"] for item in chat_history[-max_history:]]
+    input_text = "\n".join(inputs)
+
+    # Tokenize the input text
+    input_ids = tokenizer.encode(input_text, return_tensors="pt", add_special_tokens=True)
+
+    # Generate response
+    with torch.no_grad():
+        output = model.generate(input_ids, max_length=100, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id)
+
+    # Decode response and extract bot message
+    bot_response = tokenizer.decode(output[:, input_ids.shape[-1]:][0], skip_special_tokens=True)
+
+    return bot_response
+
+@app.route("/")
+def index():
+    return jsonify({"status" : True})
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=7860)

requirements.txt

@@ -0,0 +1,6 @@
+Flask==2.0.2
+python-dotenv==0.19.2
+transformers>=4.0.0
+torch>=1.8.0
+nltk>=3.6.0
+accelerate>=0.20.3

static/index.html

@@ -0,0 +1,5 @@
+<h1>
+    This is flask test app
+</h1>
+
+<p>Hello flask ?</p>