Fingpt: Democratizing internet-scale data for financial large language models
Large language models (LLMs) have demonstrated remarkable proficiency in
understanding and generating human-like texts, which may potentially revolutionize the …
understanding and generating human-like texts, which may potentially revolutionize the …
Differentially private low-rank adaptation of large language model using federated learning
The surge in interest and application of large language models (LLMs) has sparked a drive
to fine-tune these models to suit specific applications, such as finance and medical science …
to fine-tune these models to suit specific applications, such as finance and medical science …
One less reason for filter pruning: Gaining free adversarial robustness with structured grouped kernel pruning
Densely structured pruning methods utilizing simple pruning heuristics can deliver
immediate compression and acceleration benefits with acceptable benign performances …
immediate compression and acceleration benefits with acceptable benign performances …
DSpar: An embarrassingly simple strategy for efficient GNN training and inference via degree-based sparsification
Running Graph Neural Networks (GNNs) on large graphs suffers from notoriously
inefficiency. This is attributed to the sparse graph-based operations, which is hard to be …
inefficiency. This is attributed to the sparse graph-based operations, which is hard to be …
Intelligent practices of large language models in digital government services
J Han, J Lu, Y Xu, J You, B Wu - IEEE Access, 2024 - ieeexplore.ieee.org
Large language models have been widely used in open-domain tasks with significant
results, as well as being able to perform zero-sample closed-ended questions based on …
results, as well as being able to perform zero-sample closed-ended questions based on …
Large language models as faithful explainers
Large Language Models (LLMs) have recently become proficient in addressing complex
tasks by utilizing their rich internal knowledge and reasoning ability. Consequently, this …
tasks by utilizing their rich internal knowledge and reasoning ability. Consequently, this …
TBA: Faster Large Language Model Training Using SSD-Based Activation Offloading
The growth rate of the GPU memory capacity has not been able to keep up with that of the
size of large language models (LLMs), hindering the model training process. In particular …
size of large language models (LLMs), hindering the model training process. In particular …
FFSplit: Split Feed-Forward Network For Optimizing Accuracy-Efficiency Trade-off in Language Model Inference
Z Liu, Q Song, QC **ao, SK Selvaraj… - arxiv preprint arxiv …, 2024 - arxiv.org
The large number of parameters in Pretrained Language Models enhance their
performance, but also make them resource-intensive, making it challenging to deploy them …
performance, but also make them resource-intensive, making it challenging to deploy them …
ViTeGNN: Towards Versatile Inference of Temporal Graph Neural Networks on FPGA
Temporal Graph Neural Networks (TGNNs) are powerful models to capture temporal,
structural, and contextual information on temporal graphs, outperforming other methods in …
structural, and contextual information on temporal graphs, outperforming other methods in …
Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity
Zeroth-order optimization (ZO) is a memory-efficient strategy for fine-tuning Large Language
Models using only forward passes. However, the application of ZO fine-tuning in memory …
Models using only forward passes. However, the application of ZO fine-tuning in memory …