Create pre-requirements.txt

.gitignore

@@ -1 +0,0 @@
-*.keras

app.py

@@ -1,88 +1,7 @@
-# Author: Bastien & Pascal
-# Date: 2/25/2024
-# Project: SAE-GPT2 | BUT 3 Informatique - Semester 5
-
-# Import of required libraries 
-import os
-
-os.system("pip install --upgrade pip")
-os.system("pip install googletrans-py")
-os.system("pip install tensorflow==2.15.0")
-os.system("pip install keras-nlp")
-os.system("pip install -q --upgrade keras") # Upgrade Keras to version 3
-
-import time
-import keras
-import keras_nlp
-import pandas as pd
 import gradio as gr
-from googletrans import Translator
-from importHuggingFaceHubModel import from_pretrained_keras
-
-# Set Keras Backend to Tensorflow
-os.environ["KERAS_BACKEND"] = "tensorflow"
-
-# Load the fine-tuned model
-#model = keras.models.load_model("LoRA_Model_V2.keras")
-model = from_pretrained_keras('DracolIA/GPT-2-LoRA-HealthCare')
-
-translator = Translator() # Create Translator Instance
-
-# Function to generate responses from the model
-def generate_responses(question):
-    language = translator.detect(question).lang.upper() # Verify the language of the prompt
-    if language != "EN":
-        question = translator.translate(question, src=language, dest="en").text # Translation of user text to english for the model
-        
-    prompt = f"[QUESTION] {question} [ANSWER]"
-    # Generate the answer from the model and then clean and extract the real model's response from the prompt engineered string
-    output = clean_answer_text(model.generate(prompt, max_length=1024))
-    
-    # Generate the answer from the model and then clean and extract the real model's response from the prompt engineered string
-    if language != "EN":
-        output = Translator().translate(output, src="en", dest=language).text # Translation of model's text to user's language
-    
-    return output
-
-# Function clean the output of the model from the prompt engineering done in the "generate_responses" function
-def clean_answer_text(text: str) -> str:
-    # Define the start marker for the model's response
-    response_start = text.find("[ANSWER]") + len("[ANSWER]")
-
-    # Extract everything after "Doctor:"
-    response_text = text[response_start:].strip()
-    last_dot_index = response_text.rfind(".")
-    if last_dot_index != -1:
-      response_text = response_text[:last_dot_index + 1]
-
-    # Additional cleaning if necessary (e.g., removing leading/trailing spaces or new lines)
-    response_text = response_text.strip()
-
-    return response_text
-    
-
-# Define a Gradio interface
-def chat_interface(question, history_df):
-    response = generate_responses(question)
-    # Insert the new question and response at the beginning of the DataFrame
-    history_df = pd.concat([pd.DataFrame({"Question": [question], "Réponse": [response]}), history_df], ignore_index=True)
-    return response, history_df
-
-with gr.Blocks() as demo:
-    gr.HTML("""
-        <div style='width: 100%; height: 200px; background: url("https://github.com/BastienHot/SAE-GPT2/raw/70fb88500a2cc168d71e8ed635fc54492beb6241/image/logo.png") no-repeat center center; background-size: contain;'>
-            <h1 style='text-align:center; width=100%'>DracolIA - AI Question Answering for Healthcare</h1>
-        </div>
-    """)
-    with gr.Row():
-        question = gr.Textbox(label="Votre Question", placeholder="Saisissez ici...")
-        submit_btn = gr.Button("Envoyer")
-    response = gr.Textbox(label="Réponse", interactive=False)
-    
-    # Initialize an empty DataFrame to keep track of question-answer history
-    history_display = gr.Dataframe(headers=["Question", "Réponse"], values=[], interactive=False)
 
-    submit_btn.click(fn=chat_interface, inputs=[question, history_display], outputs=[response, history_display])
+def greet(name):
+    return "Hello " + name + "!!"
 
-if __name__ == "__main__":
-    demo.launch()
+iface = gr.Interface(fn=greet, inputs="text", outputs="text")
+iface.launch()

gradio.py

@@ -0,0 +1,100 @@
+# -*- coding: utf-8 -*-
+"""Untitled3.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1zwLQmMKCQKLMkJ_5Un4C6V4ajs4LYUOR
+"""
+"""
+!pip install --upgrade typing-extensions -q
+!pip install -q gradio --upgrade -q
+!pip install keras_nlp -q
+"""
+from google.colab import drive
+drive.mount('/content/drive')
+
+import os
+from tensorflow import keras
+import keras_nlp
+import gradio as gr
+import random
+import time
+
+os.environ["KERAS_BACKEND"] = "tensorflow"  # or "tensorflow" or "torch"
+keras.mixed_precision.set_global_policy("mixed_float16")
+
+preprocessor = keras_nlp.models.GPT2CausalLMPreprocessor.from_preset(
+    "gpt2_large_en",
+    sequence_length=256,
+)
+gpt2_lm = keras_nlp.models.GPT2CausalLM.from_preset(
+    "gpt2_large_en", preprocessor=preprocessor
+)
+
+gpt2_lm.load_weights('./drive/MyDrive/checkpoints/my_checkpoint')
+
+css = """
+.gradio-container {
+    background-color: transparent;
+    color: #f5f5dc;
+    border-color: #d5aa5e;
+}
+/* Styling for the chatbot  */
+.chat{
+    border-color: #d5aa5e;
+    background-color:#22201f;
+    background-image: url('https://github.com/BastienHot/SAE-GPT2/blob/70fb88500a2cc168d71e8ed635fc54492beb6241/image/logo.png');
+    background-size: cover;
+    background-position: center;
+}
+
+/* Styling for the user */
+.user{
+    background-color: #957d52;
+}
+
+/* Styling for the text inside the chatbot */
+.gradio-chatbox .message-container .message-right {
+    color: #f5f5dc; /* Antique white text color */
+    border-color: #d5aa5e;
+    background-color: red;
+}
+
+.md svelte-1syupzx chatbot{
+  border-color: #d5aa5e;
+    background-color: #3e3836;
+}
+
+.message user svelte-1lcyrx4 message-bubble-border {
+  border-color: #3e3836;
+}
+
+
+"""
+
+def predict(text):
+    # Simulating model prediction
+    return gpt2_lm.generate(text)
+
+with gr.Blocks(css=css) as demo:
+    chatbot = gr.Chatbot(elem_classes="chat")
+    msg = gr.Textbox(elem_classes="user")
+    clear = gr.ClearButton([msg, chatbot])
+
+    def respond(message, chat_history):
+        bot_message = predict(message)
+        # Ajouter une classe pour la partie bot_message
+        bot_message_html = f'<div class="bot-message">{bot_message}</div>'
+        # Ajouter une classe pour la partie message
+        user_message_html = f'<div class="user-message">{message}</div>'
+        chat_history.append((user_message_html, bot_message_html))
+        time.sleep(2)
+        return "", chat_history
+
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+
+
+if __name__ == "__main__":
+    demo.launch(debug=True, share=True)
+

importHuggingFaceHubModel.py

@@ -1,164 +0,0 @@
-# Author : ZHAN Pascal
-# Date 09/03/2025
-# Project: SAE-GPT2 | BUT 3 Informatique - Semester 5
-
-"""
-https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/keras_mixin.py#L397
-It seems the function 'from_pretrained_keras' from Hugging Face's 'huggingface_hub' is not working.
-Let's rewrite the code to fix it locally.
-
-To load the model, it's using 'tf.keras.models.load_model', but it's providing a folder instead of the path to the model file
-So, we'll search for the first file with the .keras extension in the folder. If None is found then it will raise an error.
-"""
-
-from huggingface_hub import ModelHubMixin, snapshot_download
-import os
-from huggingface_hub.utils import (
-    get_tf_version,
-    is_tf_available,
-)
-
-def from_pretrained_keras(*args, **kwargs) -> "KerasModelHubMixin":
-    r"""
-    Instantiate a pretrained Keras model from a pre-trained model from the Hub.
-    The model is expected to be in `SavedModel` format.
-    Args:
-        pretrained_model_name_or_path (`str` or `os.PathLike`):
-            Can be either:
-                - A string, the `model id` of a pretrained model hosted inside a
-                  model repo on huggingface.co. Valid model ids can be located
-                  at the root-level, like `bert-base-uncased`, or namespaced
-                  under a user or organization name, like
-                  `dbmdz/bert-base-german-cased`.
-                - You can add `revision` by appending `@` at the end of model_id
-                  simply like this: `dbmdz/bert-base-german-cased@main` Revision
-                  is the specific model version to use. It can be a branch name,
-                  a tag name, or a commit id, since we use a git-based system
-                  for storing models and other artifacts on huggingface.co, so
-                  `revision` can be any identifier allowed by git.
-                - A path to a `directory` containing model weights saved using
-                  [`~transformers.PreTrainedModel.save_pretrained`], e.g.,
-                  `./my_model_directory/`.
-                - `None` if you are both providing the configuration and state
-                  dictionary (resp. with keyword arguments `config` and
-                  `state_dict`).
-        force_download (`bool`, *optional*, defaults to `False`):
-            Whether to force the (re-)download of the model weights and
-            configuration files, overriding the cached versions if they exist.
-        resume_download (`bool`, *optional*, defaults to `False`):
-            Whether to delete incompletely received files. Will attempt to
-            resume the download if such a file exists.
-        proxies (`Dict[str, str]`, *optional*):
-            A dictionary of proxy servers to use by protocol or endpoint, e.g.,
-            `{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}`. The
-            proxies are used on each request.
-        token (`str` or `bool`, *optional*):
-            The token to use as HTTP bearer authorization for remote files. If
-            `True`, will use the token generated when running `transformers-cli
-            login` (stored in `~/.huggingface`).
-        cache_dir (`Union[str, os.PathLike]`, *optional*):
-            Path to a directory in which a downloaded pretrained model
-            configuration should be cached if the standard cache should not be
-            used.
-        local_files_only(`bool`, *optional*, defaults to `False`):
-            Whether to only look at local files (i.e., do not try to download
-            the model).
-        model_kwargs (`Dict`, *optional*):
-            model_kwargs will be passed to the model during initialization
-    <Tip>
-    Passing `token=True` is required when you want to use a private
-    model.
-    </Tip>
-    """
-    return KerasModelHubMixin.from_pretrained(*args, **kwargs)
-
-
-class KerasModelHubMixin(ModelHubMixin):
-    """
-    Implementation of [`ModelHubMixin`] to provide model Hub upload/download
-    capabilities to Keras models.
-    ```python
-    >>> import tensorflow as tf
-    >>> from huggingface_hub import KerasModelHubMixin
-    >>> class MyModel(tf.keras.Model, KerasModelHubMixin):
-    ...     def __init__(self, **kwargs):
-    ...         super().__init__()
-    ...         self.config = kwargs.pop("config", None)
-    ...         self.dummy_inputs = ...
-    ...         self.layer = ...
-    ...     def call(self, *args):
-    ...         return ...
-    >>> # Initialize and compile the model as you normally would
-    >>> model = MyModel()
-    >>> model.compile(...)
-    >>> # Build the graph by training it or passing dummy inputs
-    >>> _ = model(model.dummy_inputs)
-    >>> # Save model weights to local directory
-    >>> model.save_pretrained("my-awesome-model")
-    >>> # Push model weights to the Hub
-    >>> model.push_to_hub("my-awesome-model")
-    >>> # Download and initialize weights from the Hub
-    >>> model = MyModel.from_pretrained("username/super-cool-model")
-    ```
-    """
-
-    @classmethod
-    def _from_pretrained(
-        cls,
-        model_id,
-        revision,
-        cache_dir,
-        force_download,
-        proxies,
-        resume_download,
-        local_files_only,
-        token,
-        **model_kwargs,
-    ):
-        """Here we just call [`from_pretrained_keras`] function so both the mixin and
-        functional APIs stay in sync.
-                TODO - Some args above aren't used since we are calling
-                snapshot_download instead of hf_hub_download.
-        """
-        if is_tf_available():
-            import tensorflow as tf
-        else:
-            raise ImportError("Called a TensorFlow-specific function but could not import it.")
-
-        # TODO - Figure out what to do about these config values. Config is not going to be needed to load model
-        cfg = model_kwargs.pop("config", None)
-
-        # Root is either a local filepath matching model_id or a cached snapshot
-        if not os.path.isdir(model_id):
-            storage_folder = snapshot_download(
-                repo_id=model_id,
-                revision=revision,
-                cache_dir=cache_dir,
-                library_name="keras",
-                library_version=get_tf_version(),
-            )
-        else:
-            storage_folder = model_id
-
-        files = os.listdir(storage_folder)
-        modelFileName = None
-        nbModel = 0
-        for file in files :
-          if file.endswith(".keras"):
-            modelFileName = file
-            nbModel +=1
-        
-        if modelFileName==None:
-          raise ValueError("Repository does not have model that ends with .keras!!!")
-
-        if nbModel > 1:
-          raise ValueError("Too many models!!!")
-
-        modelPath = storage_folder + '/' + modelFileName
-
-        model = tf.keras.models.load_model(modelPath, **model_kwargs)
-
-        # For now, we add a new attribute, config, to store the config loaded from the hub/a local dir.
-        model.config = cfg
-        
-        return model

pre-requirements.txt

@@ -0,0 +1 @@
+pip==24.0

requirements.txt

@@ -1 +1,3 @@
-gradio
+gradio
+keras_nlp
+typing-extensions