"pull and shock"

README.md

@@ -11,3 +11,13 @@ license: apache-2.0
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+## Environment
+```shell
+# If you have conda, we recommend you to build a conda environment called "adl-hw1"
+make
+conda activate adl-hw1
+pip install -r requirements.txt
+# Otherwise
+pip install -r requirements.in
+```

cache/intent/embeddings.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f48c2a4bb711ddd28a95f849b676ab6c76a4aeff3ba01976ccea97a4808ce790
-size 7789931

cache/slot/embeddings.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:faba49b73dfdd2a98dbbfe7b53eed50b8edd9df716169e8f837558c5e24c42bf
-size 4941099

cache/slot/tag2idx.json

@@ -1,11 +0,0 @@
-{
-  "O": 0,
-  "B-date": 1,
-  "I-time": 2,
-  "B-time": 3,
-  "B-last_name": 4,
-  "I-people": 5,
-  "B-people": 6,
-  "I-date": 7,
-  "B-first_name": 8
-}

cache/slot/vocab.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c711af8ba9cba928df00a20913b2bcdd0738ab3b9210b4b9f10d0ff9dcf27f16
-size 49861

ckpt/intent/model_checkpoint.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65fdb8e191b37fc6866acd1699f8978736bfb975b176d5ee0464f43301d928e8
-size 56947301
+oid sha256:2c69530b46831942e17a75192a402d6a699d7de48340fbf336f964277742af95
+size 74048714

dataset.py

@@ -1,74 +0,0 @@
-from typing import List, Dict
-
-import torch
-
-from torch.utils.data import Dataset
-
-from utils import Vocab
-
-
-class SeqClsDataset(Dataset):
-    def __init__(
-        self,
-        data: List[Dict],
-        vocab: Vocab,
-        label_mapping: Dict[str, int],
-        max_len: int,
-    ):
-        self.data = data
-        self.vocab = vocab
-        self.label_mapping = label_mapping
-        self._idx2label = {idx: intent for intent, idx in self.label_mapping.items()}
-        self.max_len = max_len
-
-    def __len__(self) -> int:
-        return len(self.data)
-
-    def __getitem__(self, index) -> Dict:
-        instance = self.data[index]
-        return instance
-
-    @property
-    def num_classes(self) -> int:
-        return len(self.label_mapping)
-
-    def collate_fn(self, samples: List[Dict]) -> Dict:
-        # sample就是batch data
-        # collate_fn幫你把batch data編碼成詞彙的索引
-        # batch[0] = {'text': '~', 'intent': '~', 'id': 'train-0'}
-
-        # 提取所有樣本的文本數據和標籤數據
-        texts = samples["text"]
-        labels = samples["intent"]
-
-        # 使用 vocab 將文本數據轉換為整數索引序列，並指定最大長度
-        encoded_texts = self.vocab.encode_batch([text.split() for text in texts], to_len=self.max_len)
-
-        # 將標籤數據轉換為整數索引序列
-        encoded_labels = [self.label_mapping[label] for label in labels]
-
-        # 將整數索引序列轉換為 PyTorch 張量
-        encoded_text = torch.tensor(encoded_texts)
-        encoded_label = torch.tensor(encoded_labels)
-
-        # 創建批次數據字典
-        batch_data = {
-            "encoded_text": encoded_text,
-            "encoded_label": encoded_label
-        }
-
-        return batch_data
-
-    def label2idx(self, label: str):
-        return self.label_mapping[label]
-
-    def idx2label(self, idx: int):
-        return self._idx2label[idx]
-
-
-class SeqTaggingClsDataset(SeqClsDataset):
-    ignore_idx = -100
-
-    def collate_fn(self, samples):
-        # TODO: implement collate_fn
-        raise NotImplementedError

model.py

@@ -3,8 +3,7 @@ from typing import Dict
 import torch
 import torch.nn as nn
 
-# Set device
-device = "cuda" if torch.cuda.is_available() else "cpu"
+device = "cpu"
 
 class SeqClassifier(nn.Module):
     def __init__(
@@ -68,9 +67,3 @@ class SeqClassifier(nn.Module):
         # 通過全連接層
         logits = self.fc(combined_hidden_state)
         return logits  # 返回預測結果
-
-
-class SeqTagger(SeqClassifier):
-    def forward(self, batch) -> Dict[str, torch.Tensor]:
-        # TODO: implement model forward
-        raise NotImplementedError

requirements.in → requirements.txt

@@ -7,4 +7,5 @@ numpy
 pandas
 scikit-learn==1.1.2
 transformers[torch]
-datasets
+datasets
+huggingface_hub

seafoam.py

@@ -0,0 +1,58 @@
+from __future__ import annotations
+from typing import Iterable
+import gradio as gr
+from gradio.themes.base import Base
+from gradio.themes.utils import colors, fonts, sizes
+import time
+
+class Seafoam(Base):
+    def __init__(
+        self,
+        *,
+        primary_hue: colors.Color | str = colors.emerald,
+        secondary_hue: colors.Color | str = colors.blue,
+        neutral_hue: colors.Color | str = colors.blue,
+        spacing_size: sizes.Size | str = sizes.spacing_md,
+        radius_size: sizes.Size | str = sizes.radius_md,
+        text_size: sizes.Size | str = sizes.text_lg,
+        font: fonts.Font
+        | str
+        | Iterable[fonts.Font | str] = (
+            fonts.GoogleFont("Quicksand"),
+            "ui-sans-serif",
+            "sans-serif",
+        ),
+        font_mono: fonts.Font
+        | str
+        | Iterable[fonts.Font | str] = (
+            fonts.GoogleFont("IBM Plex Mono"),
+            "ui-monospace",
+            "monospace",
+        ),
+    ):
+        super().__init__(
+            primary_hue=primary_hue,
+            secondary_hue=secondary_hue,
+            neutral_hue=neutral_hue,
+            spacing_size=spacing_size,
+            radius_size=radius_size,
+            text_size=text_size,
+            font=font,
+            font_mono=font_mono,
+        )
+        super().set(
+            body_background_fill="repeating-linear-gradient(45deg, *primary_200, *primary_200 10px, *primary_50 10px, *primary_50 20px)",
+            body_background_fill_dark="repeating-linear-gradient(45deg, *primary_800, *primary_800 10px, *primary_900 10px, *primary_900 20px)",
+            button_primary_background_fill="linear-gradient(90deg, *primary_300, *secondary_400)",
+            button_primary_background_fill_hover="linear-gradient(90deg, *primary_200, *secondary_300)",
+            button_primary_text_color="white",
+            button_primary_background_fill_dark="linear-gradient(90deg, *primary_600, *secondary_800)",
+            slider_color="*secondary_300",
+            slider_color_dark="*secondary_600",
+            block_title_text_weight="600",
+            block_border_width="3px",
+            block_shadow="*shadow_drop_lg",
+            button_shadow="*shadow_drop_lg",
+            button_large_padding="32px",
+        )
+