no code implementations • 24 Apr 2024 • Cheng Kang, Daniel Novak, Katerina Urbanova, Yuqing Cheng, Yong Hu
Large language models (LLMs) have demonstrated impressive generalization capabilities on specific tasks with human-written instruction data.
no code implementations • 15 Feb 2024 • Cheng Kang, Xinye Chen, Yong Hu, Daniel Novak
To further enhance their portability of independent deployment as well as improve their stability evaluated by language perplexity, we propose a novel approach called the Quantized Embedding Controllable Diffusion Language Model (QE-CDLM).
no code implementations • 9 Oct 2023 • Cheng Kang, Xujing Yao
How can the stability and efficiency of Artificial Neural Networks (ANNs) be ensured through a systematic analysis method?
1 code implementation • 1 Aug 2022 • Cheng Kang, Jindich Prokop, Lei Tong, Huiyu Zhou, Yong Hu, Daneil Novak
As for the gate with inhibition MLPs on DeBERTa (giDeBERTa) fine-tuning, we find it can achieve appealing results on most parts of NLU tasks without any extra pretraining again.