language:
- en
tags:
- sentiment-analysis
- distilbert
- text-classification
- nlp
license: apache-2.0
datasets:
- amazon_polarity
metrics:
- accuracy
- f1
model-index:
- name: fine-tuned-distilbert
results:
- task:
type: text-classification
name: Sentiment Analysis
dataset:
name: Amazon Polarity
type: amazon_polarity
metrics:
- name: Accuracy
type: accuracy
value: 0.9
- name: F1
type: f1
value: 0.89
Fine-Tuned DistilBERT for Sentiment Analysis
Model Description
This model is a fine-tuned version of distilbert-base-uncased on the amazon_polarity dataset. It is designed for binary sentiment classification, predicting whether a given text expresses a positive (1) or negative (0) sentiment. The model leverages the lightweight architecture of DistilBERT, making it efficient for deployment while maintaining strong performance.
- Developed by: [Jack.RX Tech]
- Model Type: Transformer-based text classification
- Base Model:
distilbert-base-uncased - Language: English
- License: Apache 2.0
Intended Uses
This model is intended for sentiment analysis tasks, particularly in analyzing product reviews or user feedback. It can be used in:
- E-commerce platforms to monitor customer opinions.
- Social media analysis for brand reputation management.
- Market research to gauge consumer sentiment.
Direct Use
The model can classify text directly without additional fine-tuning for similar binary sentiment tasks.
Downstream Use
It can be further fine-tuned for domain-specific sentiment analysis (e.g., medical reviews, movie critiques).
How to Use
Python Code Example
Below is an example of how to load and use the model with the transformers library:
from transformers import AutoModelForSequenceClassification, AutoTokenizer
# 加载模型和tokenizer
model_name = "huevan/distilbert-base-uncased-rx" # 替换为你的仓库名
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
# 输入文本
text = "I love this product, it's amazing!"
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=128)
# 预测
model.eval()
with torch.no_grad():
outputs = model(**inputs)
prediction = outputs.logits.argmax(-1).item()
sentiment = "positive" if prediction == 1 else "negative"
print(f"Sentiment: {sentiment}") # 输出: positive