Fix bug

.gitignore

@@ -0,0 +1,164 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+zemo*.py

README.md

@@ -1,3 +1,21 @@
+---
+license: apache-2.0
+license_link: https://huggingface.co/GlowCheese/minBERT/blob/main/LICENSE
+language:
+- en
+base_model:
+- google-research/bert
+pipeline_tag: sentiment-analysis
+library_name: transformers
+tags:
+- bert
+- minbert
+- trainsformer
+- sentiment
+- tokenizer
+- classification
+---
+
 # CS 224N Default Final Project - Multitask BERT
 
 This is the default final project for the Stanford CS 224N class. Please refer to the project handout on the course website for detailed instructions and an overview of the codebase.

zemo1.py

@@ -1,53 +0,0 @@
-import torch
-import torch.nn as nn
-from tqdm import tqdm
-import torch.optim as optim
-
-# Bước 1: Chuẩn bị dữ liệu mẫu
-# Dữ liệu giả: mỗi dòng là [giờ học, giờ giải trí, giờ ngủ], điểm trung bình
-data = [
-    [2, 1, 7, 6.0],
-    [3, 2, 6, 7.5],
-    [1, 3, 8, 5.5],
-    [4, 1, 6, 8.0],
-    [5, 0, 5, 9.0],
-    [6, 0, 6, 9.5]
-]
-
-# Tách đặc trưng (features) và mục tiêu (target)
-X = torch.tensor([row[:3] for row in data], dtype=torch.float32)  # Giờ học, giờ giải trí, giờ ngủ
-y = torch.tensor([[row[3]] for row in data], dtype=torch.float32)  # Điểm trung bình
-
-# Bước 2: Xây dựng mô hình
-class StudentGradeModel(nn.Module):
-    def __init__(self):
-        super(StudentGradeModel, self).__init__()
-        self.linear = nn.Linear(3, 1)  # 3 đầu vào, 1 đầu ra
-
-    def forward(self, x):
-        return self.linear(x)
-
-model = StudentGradeModel()
-
-# Bước 3: Định nghĩa hàm mất mát và bộ tối ưu
-criterion = nn.MSELoss()
-optimizer = optim.SGD(model.parameters(), lr=0.01)
-
-# Bước 4: Huấn luyện mô hình
-for epoch in tqdm(range(10000), desc="Training Epochs"):
-    optimizer.zero_grad()  # Xóa gradient cũ
-    output = model(X)      # Truyền dữ liệu qua mô hình
-    loss = criterion(output, y)  # Tính mất mát
-    loss.backward()        # Tính gradient
-    optimizer.step()       # Cập nhật trọng số
-
-    # In loss để theo dõi quá trình huấn luyện
-    if (epoch + 1) % 1000 == 0:
-        tqdm.write(f'Epoch [{epoch + 1}/10000], Loss: {loss.item():.4f}')
-
-# Bước 5: Dự đoán thử với một học sinh mới
-model.eval()
-with torch.no_grad():
-    test_input = torch.tensor([[4, 1, 6]], dtype=torch.float32)  # Ví dụ: 4 giờ học, 1 giờ giải trí, 6 giờ ngủ
-    prediction = model(test_input)
-    print("Dự đoán điểm trung bình:", prediction.item())

zemo2.py

@@ -1,41 +0,0 @@
-import torch
-import torch.nn as nn
-
-# Xây dựng mô hình RNN
-class RNNModel(nn.Module):
-    def __init__(self, input_size, hidden_size, output_size):
-        super(RNNModel, self).__init__()
-        self.rnn = nn.RNN(input_size, hidden_size, batch_first=True)  # Định nghĩa RNN
-        self.fc = nn.Linear(hidden_size, output_size)  # Lớp fully connected để dự đoán output
-
-    def forward(self, x):
-        out, _ = self.rnn(x)  # Lấy output từ RNN
-        out = out[:, -1, :]  # Lấy output của bước cuối cùng (nếu dữ liệu có nhiều bước thời gian)
-        out = self.fc(out)  # Dự đoán output
-        return out
-
-# Khởi tạo mô hình
-input_size = 10  # Kích thước đầu vào
-hidden_size = 20  # Số lượng hidden units
-output_size = 1  # Đầu ra (ví dụ: hồi quy)
-model = RNNModel(input_size, hidden_size, output_size)
-
-# Khởi tạo dữ liệu giả
-X = torch.randn(32, 5, 10)  # 32 samples, 5 bước thời gian, mỗi bước có 10 đặc trưng
-y = torch.randn(32, 1)  # 32 samples, 1 giá trị đầu ra cho mỗi sample
-
-# Hàm mất mát và bộ tối ưu
-criterion = nn.MSELoss()
-optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
-
-# Huấn luyện mô hình
-for epoch in range(100):
-    model.train()
-    optimizer.zero_grad()
-    output = model(X)  # Truyền dữ liệu qua mô hình
-    loss = criterion(output, y)  # Tính mất mát
-    loss.backward()  # Tính gradient
-    optimizer.step()  # Cập nhật trọng số
-
-    if (epoch + 1) % 10 == 0:
-        print(f'Epoch [{epoch+1}/100], Loss: {loss.item():.4f}')

zemo3.py

@@ -1,32 +0,0 @@
-import torch
-from tokenizer import BertTokenizer
-from torch import nn
-from bert import BertModel
-
-# Initialize the BERT tokenizer
-tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-
-# Example sentence
-sentences = [
-    "She loves reading novels in her free time",
-    "An apple a day keeps the doctor away",
-    "If you can't explain it simply, you don't understand it well enough."
-]
-
-# Tokenize and encode the sentence
-encoding = tokenizer.batch_encode_plus(
-    sentences,
-    max_length=512,
-    padding='max_length',
-    truncation=True,
-    return_tensors='pt'
-)
-
-# Get the token IDs from the encoding
-input_ids = encoding['input_ids']
-attention_mask = encoding['attention_mask']
-
-model = BertModel.from_pretrained('bert-base-uncased')
-
-assert isinstance(model, BertModel)
-print(model.embed(input_ids).size())