|
--- |
|
language: en |
|
tags: |
|
- emotion-classification |
|
- bert |
|
- lora |
|
license: mit |
|
--- |
|
|
|
# Emotion Classification Model |
|
|
|
This model is a fine-tuned version of `bert-base-uncased` on the "dair-ai/emotion" dataset, using LoRA (Low-Rank Adaptation) for efficient fine-tuning. |
|
|
|
label_list={"sadness", "joy", "love", "anger" ,"fear","surprise"} |
|
|
|
## Model description |
|
|
|
[Describe your model, its architecture, and the task it performs] |
|
|
|
## Intended uses & limitations |
|
|
|
[Describe what the model is intended for and any limitations] |
|
|
|
## Training and evaluation data |
|
|
|
The model was trained on the "dair-ai/emotion" dataset. |
|
|
|
## Training procedure |
|
|
|
[Describe your training procedure, hyperparameters, etc.] |
|
|
|
## Eval results |
|
|
|
[Include your evaluation results] |
|
|
|
## How to use |
|
|
|
Here's how you can use the model: |
|
|
|
```python |
|
from transformers import AutoModelForSequenceClassification, AutoTokenizer |
|
|
|
model = AutoModelForSequenceClassification.from_pretrained("ahmetyaylalioglu/text-emotion-classifier") |
|
tokenizer = AutoTokenizer.from_pretrained("ahmetyaylalioglu/text-emotion-classifier") |
|
|
|
text = "I am feeling very happy today!" |
|
inputs = tokenizer(text, return_tensors="pt") |
|
outputs = model(**inputs) |
|
predictions = outputs.logits.argmax(-1) |
|
print(model.config.id2label[predictions.item()]) |
