Current language models usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and online serving in real-life applications due to latency and capacity constraints. In this project, we release a light weight korean language model to address the aforementioned shortcomings of existing language models.
Quick tour
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("BM-K/KoMiniLM-68M") # 68M model
model = AutoModel.from_pretrained("BM-K/KoMiniLM-68M")
inputs = tokenizer("안녕 세상아!", return_tensors="pt")
outputs = model(**inputs)
Self-Attention Distribution and Self-Attention Value-Relation
[Wang et al., 2020]
were distilled from each discrete layer of the teacher model to the student model. Wang et al. distilled in the last layer of the transformer, but that was not the case in this project.
More Information About KoMiniLM-68M huggingface.co Model
KoMiniLM-68M huggingface.co
KoMiniLM-68M huggingface.co is an AI model on huggingface.co that provides KoMiniLM-68M's model effect (), which can be used instantly with this BM-K KoMiniLM-68M model. huggingface.co supports a free trial of the KoMiniLM-68M model, and also provides paid use of the KoMiniLM-68M. Support call KoMiniLM-68M model through api, including Node.js, Python, http.
KoMiniLM-68M huggingface.co is an online trial and call api platform, which integrates KoMiniLM-68M's modeling effects, including api services, and provides a free online trial of KoMiniLM-68M, you can try KoMiniLM-68M online for free by clicking the link below.
BM-K KoMiniLM-68M online free url in huggingface.co:
KoMiniLM-68M is an open source model from GitHub that offers a free installation service, and any user can find KoMiniLM-68M on GitHub to install. At the same time, huggingface.co provides the effect of KoMiniLM-68M install, users can directly use KoMiniLM-68M installed effect in huggingface.co for debugging and trial. It also supports api for free installation.