Yi Dong – NVIDIA Technical Blog News and tutorials for developers, data scientists, and IT admins 2024-05-02T16:47:04Z http://www.open-lab.net/blog/feed/ Yi Dong <![CDATA[Announcing NVIDIA SteerLM: A Simple and Practical Technique to Customize LLMs During Inference]]> http://www.open-lab.net/blog/?p=68954 2024-05-02T16:47:04Z 2023-10-11T14:30:00Z With the advent of large language models (LLMs) such as GPT-3, Megatron-Turing, Chinchilla, PaLM-2, Falcon, and Llama 2, remarkable progress in natural language...]]>

With the advent of large language models (LLMs) such as GPT-3, Megatron-Turing, Chinchilla, PaLM-2, Falcon, and Llama 2, remarkable progress in natural language generation has been made in recent years. However, despite their ability to produce human-like text, ‌foundation LLMs can fail to provide helpful and nuanced responses aligned with user preferences. The current approach to improving…

Source

]]>
0
Yi Dong <![CDATA[Adapting P-Tuning to Solve Non-English Downstream Tasks]]> http://www.open-lab.net/blog/?p=50352 2023-06-12T09:18:04Z 2022-07-13T06:59:00Z With the increasing demand for access to pretrained large language model (LLM) weights, the climate around LLM sharing is changing. Recently, Meta released Open...]]>

With the increasing demand for access to pretrained large language model (LLM) weights, the climate around LLM sharing is changing. Recently, Meta released Open Pretrained Transformer, a language model with 175 billion parameters. BigScience is on schedule to release its multilingual language model with 176 billion parameters in a few months. As more LLMs become available…

Source

]]>
0
Yi Dong <![CDATA[Generating Synthetic Data with Transformers: A Solution for Enterprise Data Challenges]]> http://www.open-lab.net/blog/?p=47308 2023-03-14T23:24:51Z 2022-05-09T16:00:00Z Big data, new algorithms, and fast computation are three main factors that make the modern AI revolution possible. However, data poses many challenges for...]]>

Big data, new algorithms, and fast computation are three main factors that make the modern AI revolution possible. However, data poses many challenges for enterprises: difficulty in data labeling, ineffective data governance, limited data availability, data privacy, and so on. Synthetically generated data is a potential solution to address these challenges because it generates data points by…

Source

]]>
0
Yi Dong <![CDATA[Accelerated Portfolio Construction with Numba and Dask in Python]]> http://www.open-lab.net/blog/?p=38831 2023-03-14T18:32:08Z 2021-10-21T18:30:00Z Python is no stranger to data scientists. It ranks as the most popular computer language and is widely used for all kinds of tasks. Though Python is notoriously...]]>

Python is no stranger to data scientists. It ranks as the most popular computer language and is widely used for all kinds of tasks. Though Python is notoriously slow when the code is interpreted at runtime, many popular libraries make it run efficiently on GPUs for certain data science work. For example, popular deep learning frameworks such as TensorFlow, and PyTorch help AI researchers to…

Source

]]>
0
Yi Dong <![CDATA[Training and Fine-tuning BERT Using NVIDIA NGC]]> http://www.open-lab.net/blog/?p=17909 2022-08-21T23:40:09Z 2020-06-16T17:25:49Z Imagine an AI program that can understand language better than humans can. Imagine building your own personal Siri or Google Search for a customized domain or...]]>

Imagine an AI program that can understand language better than humans can. Imagine building your own personal Siri or Google Search for a customized domain or application. Google BERT (Bidirectional Encoder Representations from Transformers) provides a game-changing twist to the field of natural language processing (NLP). BERT runs on supercomputers powered by NVIDIA GPUs to train its…

Source

]]>
0
Yi Dong <![CDATA[Accelerating Python for Exotic Option Pricing]]> http://www.open-lab.net/blog/?p=16723 2022-08-21T23:39:50Z 2020-03-19T22:49:44Z In finance, computation efficiency can be directly converted to trading profits sometimes. Quants are facing the challenges of trading off research efficiency...]]>

Source

]]>
0
���˳���97caoporen����