Deberta V3 Base Mnli Fever Anli

🚀 DeBERTa-v3-base-mnli-fever-anli

該模型在文本分類和零樣本分類任務中表現出色，基於特定數據集訓練，能有效處理自然語言推理問題，為相關領域研究和應用提供了有力支持。

🚀 快速開始

簡單的零樣本分類管道

#!pip install transformers[sentencepiece]
from transformers import pipeline
classifier = pipeline("zero-shot-classification", model="MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli")
sequence_to_classify = "Angela Merkel is a politician in Germany and leader of the CDU"
candidate_labels = ["politics", "economy", "entertainment", "environment"]
output = classifier(sequence_to_classify, candidate_labels, multi_label=False)
print(output)

NLI使用案例

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")

model_name = "MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

premise = "I first thought that I liked the movie, but upon second thought it was actually disappointing."
hypothesis = "The movie was good."

input = tokenizer(premise, hypothesis, truncation=True, return_tensors="pt")
output = model(input["input_ids"].to(device))  # device = "cuda:0" or "cpu"
prediction = torch.softmax(output["logits"][0], -1).tolist()
label_names = ["entailment", "neutral", "contradiction"]
prediction = {name: round(float(pred) * 100, 1) for pred, name in zip(prediction, label_names)}
print(prediction)

✨ 主要特性

• 該模型在MultiNLI、Fever - NLI和Adversarial - NLI (ANLI)數據集上進行訓練，包含763913個NLI假設 - 前提對。
• 此基礎模型在ANLI基準測試中幾乎優於所有大型模型。
• 基礎模型是微軟的DeBERTa - v3 - base，DeBERTa的v3變體通過不同的預訓練目標，顯著優於該模型的先前版本。

📦 安裝指南

在使用模型前，你需要安裝transformers庫，可使用以下命令進行安裝：

#!pip install transformers[sentencepiece]

💻 使用示例

基礎用法

#!pip install transformers[sentencepiece]
from transformers import pipeline
classifier = pipeline("zero-shot-classification", model="MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli")
sequence_to_classify = "Angela Merkel is a politician in Germany and leader of the CDU"
candidate_labels = ["politics", "economy", "entertainment", "environment"]
output = classifier(sequence_to_classify, candidate_labels, multi_label=False)
print(output)

高級用法

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")

model_name = "MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

premise = "I first thought that I liked the movie, but upon second thought it was actually disappointing."
hypothesis = "The movie was good."

input = tokenizer(premise, hypothesis, truncation=True, return_tensors="pt")
output = model(input["input_ids"].to(device))  # device = "cuda:0" or "cpu"
prediction = torch.softmax(output["logits"][0], -1).tolist()
label_names = ["entailment", "neutral", "contradiction"]
prediction = {name: round(float(pred) * 100, 1) for pred, name in zip(prediction, label_names)}
print(prediction)

📚 詳細文檔

訓練數據

DeBERTa - v3 - base - mnli - fever - anli在MultiNLI、Fever - NLI和Adversarial - NLI (ANLI)數據集上進行訓練，這些數據集包含763913個NLI假設 - 前提對。

訓練過程

DeBERTa - v3 - base - mnli - fever - anli使用Hugging Face訓練器進行訓練，超參數如下：

training_args = TrainingArguments(
    num_train_epochs=3,              # total number of training epochs
    learning_rate=2e-05,
    per_device_train_batch_size=32,   # batch size per device during training
    per_device_eval_batch_size=32,    # batch size for evaluation
    warmup_ratio=0.1,                # number of warmup steps for learning rate scheduler
    weight_decay=0.06,               # strength of weight decay
    fp16=True                        # mixed precision training
)

評估結果

該模型使用MultiNLI和ANLI的測試集以及Fever - NLI的開發集進行評估，使用的指標是準確率。

🔧 技術細節

該模型基於微軟的DeBERTa - v3 - base，其v3變體通過不同的預訓練目標，顯著優於該模型的先前版本。具體可參考原始DeBERTa論文的附錄11。

📄 許可證

本項目採用MIT許可證。

⚠️ 重要提示

請參考原始DeBERTa論文和不同NLI數據集的相關文獻，以瞭解潛在的偏差。