Update README.md

README.md

@@ -1,9 +1,11 @@
 ---
-license: apache-2.0
+license: mit
 language:
 - zh
 metrics:
 - accuracy
+- f1 (macro)
+- f1 (micro)
 base_model:
 - google-bert/bert-base-chinese
 pipeline_tag: text-classification
@@ -12,6 +14,24 @@ tags:
 datasets:
 - scfengv/TVL-general-layer-dataset
 library_name: adapter-transformers
+model-index:
+- name: scfengv/TVL_GeneralLayerClassifier
+  results:
+  - task:
+      type: multi-label text-classification
+    dataset:
+      name: scfengv/TVL-general-layer-dataset
+      type: scfengv/TVL-general-layer-dataset
+    metrics:
+    - name: Accuracy
+      type: Accuracy
+      value: 0.952902
+    - name: F1 score (Micro)
+      type: F1 score (Micro)
+      value: 0.968717
+    - name: F1 score (Macro)
+      type: F1 score (Macro)
+      value: 0.970818
 ---
 # Model Card for Model ID
 
@@ -30,7 +50,7 @@ library_name: adapter-transformers
 
 ### Model Sources
 
-- **Repository:** [scfengv/NLP_DL-Topic-Modeling-for-TVL-livestream-comments](https://github.com/scfengv/NLP_DL-Topic-Modeling-for-TVL-livestream-comments)
+- **Repository:** [scfengv/NLP-Topic-Modeling-for-TVL-livestream-comments](https://github.com/scfengv/NLP-Topic-Modeling-for-TVL-livestream-comments)
 
 ## Model Inference Examples
 
@@ -43,16 +63,17 @@ python inference_example_3.py
 
 ## How to Get Started with the Model
 
+Use the code below to get started with the model.
+
 ```python
 import torch
 from transformers import BertForSequenceClassification, BertTokenizer
 
-# Load model and tokenizer
 model = BertForSequenceClassification.from_pretrained("scfengv/TVL_GeneralLayerClassifier")
 tokenizer = BertTokenizer.from_pretrained("scfengv/TVL_GeneralLayerClassifier")
 
 # Prepare your text
-text = "Your text here"
+text = "Your text here" ## Please refer to Dataset
 inputs = tokenizer(text, return_tensors = "pt", padding = True, truncation = True, max_length = 512)
 
 # Make prediction
@@ -66,16 +87,16 @@ print(predictions)
 
 ## Training Details
 
+- **Hardware Type:** NVIDIA Quadro RTX8000
+- **Library:** PyTorch
+- **Hours used:** 2hr 13mins
+- 
 ### Training Data
 
-### Training Procedure
-
-
-#### Preprocessing
-
-
-#### Training Hyperparameters
+- [scfengv/TVL-general-layer-dataset](https://huggingface.co/datasets/scfengv/TVL-general-layer-dataset)
+  - train
 
+### Training Hyperparameters
 
 The model was trained using the following hyperparameters:
 
@@ -84,29 +105,21 @@ Learning rate: 1e-05
 Batch size: 32
 Number of epochs: 10
 Optimizer: Adam
+Loss function: torch.nn.BCEWithLogitsLoss()
 ```
 
 ## Evaluation
 
-### Results
-
-- Accuracy: 0.9592504607823059
-- F1 Score (Micro): 0.9740588950133884
-- F1 Score (Macro): 0.9757074189160264
-
-## Technical Specifications
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-#### Hardware
+### Testing Data
 
-- NVIDIA Quadro RTX8000
+- [scfengv/TVL-general-layer-dataset](https://huggingface.co/datasets/scfengv/TVL-general-layer-dataset)
+  - validation
+  - Remove Emoji
+  - Emoji2Desc
+  - Remove Punctuation
 
-#### Software
+### Results (validation)
 
-- PyTorch
-- HuggingFace
+- Accuracy: 0.952902
+- F1 Score (Micro): 0.968717
+- F1 Score (Macro): 0.970818