Language model:
deepset/tinybert-6L-768D-squad2
Language:
English
Training data:
SQuAD 2.0 training set x 20 augmented + SQuAD 2.0 training set without augmentation
Eval data:
SQuAD 2.0 dev set
Infrastructure
: 1x V100 GPU
Published
: Dec 8th, 2021
Details
haystack's intermediate layer and prediction layer distillation features were used for training (based on
TinyBERT
). deepset/bert-base-uncased-squad2 was used as the teacher model and huawei-noah/TinyBERT_General_6L_768D was used as the student model.
tinybert-6l-768d-squad2 huggingface.co is an AI model on huggingface.co that provides tinybert-6l-768d-squad2's model effect (), which can be used instantly with this deepset tinybert-6l-768d-squad2 model. huggingface.co supports a free trial of the tinybert-6l-768d-squad2 model, and also provides paid use of the tinybert-6l-768d-squad2. Support call tinybert-6l-768d-squad2 model through api, including Node.js, Python, http.
tinybert-6l-768d-squad2 huggingface.co is an online trial and call api platform, which integrates tinybert-6l-768d-squad2's modeling effects, including api services, and provides a free online trial of tinybert-6l-768d-squad2, you can try tinybert-6l-768d-squad2 online for free by clicking the link below.
deepset tinybert-6l-768d-squad2 online free url in huggingface.co:
tinybert-6l-768d-squad2 is an open source model from GitHub that offers a free installation service, and any user can find tinybert-6l-768d-squad2 on GitHub to install. At the same time, huggingface.co provides the effect of tinybert-6l-768d-squad2 install, users can directly use tinybert-6l-768d-squad2 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
tinybert-6l-768d-squad2 install url in huggingface.co: