nateraw/bert-base-uncased-emotion converted to ONNX and quantized using optimum.
bert-base-uncased-emotion
Model description
bert-base-uncased finetuned on the emotion dataset using PyTorch Lightning. Sequence length 128, learning rate 2e-5, batch size 32, 2 GPUs, 4 epochs.
For more details, please see, the emotion dataset on nlp viewer.
Limitations and bias
- Not the best model, but it works in a pinch I guess...
- Code not available as I just hacked this together.
- Follow me on github to get notified when code is made available.
Training data
Data came from HuggingFace's datasets package. The data can be viewed on nlp viewer.
Training procedure
...
Eval results
val_acc - 0.931 (useless, as this should be precision/recall/f1)
The score was calculated using PyTorch Lightning metrics.
- Downloads last month
- 98
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.