MiniLMv2-goemotions-v2-onnx

Text Classification GoEmotions

This a ONNX quantized model and is fined-tuned version of MiniLMv2-L6-H384 on the on the go_emotions dataset using tasinho/text-classification-goemotions as teacher model. The original model can be found here

Optimum

Installation

Install from source:

python -m pip install optimum[onnxruntime]@git+https://github.com/huggingface/optimum.git

Run the Model

from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import AutoTokenizer, pipeline

model = ORTModelForSequenceClassification.from_pretrained('minuva/MiniLMv2-goemotions-v2-onnx', provider="CPUExecutionProvider")
tokenizer = AutoTokenizer.from_pretrained('minuva/MiniLMv2-goemotions-v2-onnx', use_fast=True, model_max_length=256, truncation=True, padding='max_length')

pipe = pipeline(task='text-classification', model=model, tokenizer=tokenizer, )
texts = ["that's wrong", "can you please answer me?"]
pipe(texts)
# [{'label': 'anger', 'score': 0.9727636575698853},
# {'label': 'love', 'score': 0.9874765276908875}]

ONNX Runtime only

A lighter solution for deployment

Installation

pip install tokenizers
pip install onnxruntime
git clone https://huggingface.co/minuva/MiniLMv2-goemotions-v2-onnx

Run the Model

import os
import numpy as np
import json

from tokenizers import Tokenizer
from onnxruntime import InferenceSession


model_name = "minuva/MiniLMv2-goemotions-v2-onnx"

tokenizer = Tokenizer.from_pretrained(model_name)
tokenizer.enable_padding(
    pad_token="<pad>",
    pad_id=1,
)
tokenizer.enable_truncation(max_length=256)
batch_size = 16

texts = ["I am angry", "I feel in love"]
outputs = []
model = InferenceSession("MiniLMv2-goemotions-v2-onnx/model_optimized_quantized.onnx", providers=['CUDAExecutionProvider'])

with open(os.path.join("MiniLMv2-goemotions-v2-onnx", "config.json"), "r") as f:
            config = json.load(f)

output_names = [output.name for output in model.get_outputs()]
input_names = [input.name for input in model.get_inputs()]

for subtexts in np.array_split(np.array(texts), len(texts) // batch_size + 1):
            encodings = tokenizer.encode_batch(list(subtexts))
            inputs = {
                "input_ids": np.vstack(
                    [encoding.ids for encoding in encodings],
                ),
                "attention_mask": np.vstack(
                    [encoding.attention_mask for encoding in encodings],
                ),
                "token_type_ids": np.vstack(
                    [encoding.type_ids for encoding in encodings],
                ),
            }

            for input_name in input_names:
                if input_name not in inputs:
                    raise ValueError(f"Input name {input_name} not found in inputs")

            inputs = {input_name: inputs[input_name] for input_name in input_names}
            output = np.squeeze(
                np.stack(
                    model.run(output_names=output_names, input_feed=inputs)
                ),
                axis=0,
            )
            outputs.append(output)

outputs = np.concatenate(outputs, axis=0)
scores = 1 / (1 + np.exp(-outputs))
results = []
for item in scores:
    labels = []
    scores = []
    for idx, s in enumerate(item):
        labels.append(config["id2label"][str(idx)])
        scores.append(float(s))
    results.append({"labels": labels, "scores": scores})


res = []

for result in results:
    joined = list(zip(result['labels'], result['scores']))
    max_score = max(joined, key=lambda x: x[1])    
    res.append(max_score)

res

# [('anger', 0.9745745062828064), ('love', 0.9884329438209534)]

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 6e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear

Metrics (comparison with teacher model)

Deployment

Check out our fast-nlp-text-emotion repository for a FastAPI based server to easily deploy this model on CPU devices.