This is an RKNN-compatible version of the distilbert/distilbert-base-uncased-finetuned-sst-2-english model. It has been optimized for Rockchip NPUs using the rk-transformers library.

Click to see the RKNN model details and usage examples

Model Details

Original Model: distilbert/distilbert-base-uncased-finetuned-sst-2-english
Target Platform: rk3588
rknn-toolkit2 Version: 2.3.2
rk-transformers Version: 0.3.0

Available Model Files

Model File	Optimization Level	Quantization	File Size
model.rknn	0	float16	131.5 MB
model_b1_s256.rknn	0	float16	129.9 MB
model_b4_s256.rknn	0	float16	135.9 MB
model_b4_s512.rknn	0	float16	141.3 MB
rknn/model_o1.rknn	1	float16	131.5 MB
rknn/model_o2.rknn	2	float16	131.5 MB
rknn/model_o3.rknn	3	float16	131.5 MB
rknn/model_w8a8.rknn	0	w8a8	67.2 MB

Usage

Installation

Install rk-transformers with inference dependencies to use this model:

pip install rk-transformers[inference]

RK-Transformers API

python

from rktransformers import RKModelForSequenceClassification
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("rk-transformers/distilbert-base-uncased-finetuned-sst-2-english")
model = RKModelForSequenceClassification.from_pretrained(
    "rk-transformers/distilbert-base-uncased-finetuned-sst-2-english",
    platform="rk3588",
    core_mask="auto",
)

inputs = tokenizer("Hello, my dog is cute", return_tensors="np")
outputs = model(**inputs)
logits = outputs.logits
print(logits.shape)

# Load specific optimized/quantized model file
model = RKModelForSequenceClassification.from_pretrained(
    "rk-transformers/distilbert-base-uncased-finetuned-sst-2-english",
    platform="rk3588",
    file_name="rknn/model_w8a8.rknn"
)

Configuration

The full configuration for all exported RKNN models is available in the config.json file.

DistilBERT base uncased finetuned SST-2

Model Details
How to Get Started With the Model
Uses
Risks, Limitations and Biases
Training

Model Details

Model Description: This model is a fine-tune checkpoint of DistilBERT-base-uncased, fine-tuned on SST-2. This model reaches an accuracy of 91.3 on the dev set (for comparison, Bert bert-base-uncased version reaches an accuracy of 92.7).

Developed by: Hugging Face
Model Type: Text Classification
Language(s): English
License: Apache-2.0
Parent Model: For more details about DistilBERT, we encourage users to check out this model card.
Resources for more information:
- Model Documentation
- DistilBERT paper

How to Get Started With the Model

Example of single-label classification:

python

import torch
from transformers import DistilBertTokenizer, DistilBertForSequenceClassification

tokenizer = DistilBertTokenizer.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
model = DistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")

inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
with torch.no_grad():
    logits = model(**inputs).logits

predicted_class_id = logits.argmax().item()
model.config.id2label[predicted_class_id]

Uses

Direct Use

This model can be used for topic classification. You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to be fine-tuned on a downstream task. See the model hub to look for fine-tuned versions on a task that interests you.

Misuse and Out-of-scope Use

The model should not be used to intentionally create hostile or alienating environments for people. In addition, the model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.

Risks, Limitations and Biases

Based on a few experimentations, we observed that this model could produce biased predictions that target underrepresented populations.

For instance, for sentences like This film was filmed in COUNTRY, this binary classification model will give radically different probabilities for the positive label depending on the country (0.89 if the country is France, but 0.08 if the country is Afghanistan) when nothing in the input indicates such a strong semantic shift. In this colab, Aurélien Géron made an interesting map plotting these probabilities for each country.

Map of positive probabilities per country.

We strongly advise users to thoroughly probe these aspects on their use-cases in order to evaluate the risks of this model. We recommend looking at the following bias evaluation datasets as a place to start: WinoBias, WinoGender, Stereoset.

Training

Training Data

The authors use the following Stanford Sentiment Treebank(sst2) corpora for the model.

Training Procedure

Fine-tuning hyper-parameters

learning_rate = 1e-5
batch_size = 32
warmup = 600
max_seq_length = 128
num_train_epochs = 3.0

rk-transformers/distilbert-base-uncased-finetuned-sst-2-english

distilbert-base-uncased-finetuned-sst-2-english (RKNN2)

Model Details

Available Model Files

Usage

Installation

RK-Transformers API

Configuration

DistilBERT base uncased finetuned SST-2

Table of Contents

Model Details

How to Get Started With the Model

Uses

Direct Use

Misuse and Out-of-scope Use

Risks, Limitations and Biases

Training

Training Data

Training Procedure

Fine-tuning hyper-parameters

rk-transformers/
distilbert-base-uncased-finetuned-sst-2-english