Search Results for author:
Found 13 papers, 5 papers with code
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
We introduce Nemotron-H, a family of 8B and 56B/47B hybrid Mamba-Transformer models designed to reduce inference cost for a given accuracy level.
Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails
As Large Language Models (LLMs) and generative AI become increasingly widespread, concerns about content safety have grown in parallel.
Unsupervised Extraction of Dialogue Policies from Conversations
Dialogue policies play a crucial role in developing task-oriented dialogue systems, yet their development and maintenance are challenging and typically require substantial effort from experts in dialogue modeling.
Nemotron-4 340B Technical Report
We release the Nemotron-4 340B model family, including Nemotron-4-340B-Base, Nemotron-4-340B-Instruct, and Nemotron-4-340B-Reward.
HelpSteer2: Open-source dataset for training top-performing reward models
Using a powerful internal base model trained on HelpSteer2, we are able to achieve the SOTA score (92. 0%) on Reward-Bench's primary dataset, outperforming currently listed open and proprietary models, as of June 12th, 2024.
CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues
Recent advancements in instruction-tuning datasets have predominantly focused on specific tasks like mathematical or logical reasoning.
Evolving Domain Adaptation of Pretrained Language Models for Text Classification
Adapting pre-trained language models (PLMs) for time-series text classification amidst evolving domain shifts (EDS) is critical for maintaining accuracy in applications like stance detection.
HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM
To alleviate this problem, we collect HelpSteer, a multi-attribute helpfulness dataset annotated for the various aspects that make responses helpful.
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF
Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values.
Prompt Learning for Domain Adaptation in Task-Oriented Dialogue
We show that canonical forms offer a promising alternative to traditional methods for intent classification.
Local Byte Fusion for Neural Machine Translation
Subword tokenization schemes are the dominant technique used in current NLP models.
Learning Improvised Chatbots from Adversarial Modifications of Natural Language Feedback
The ubiquitous nature of chatbots and their interaction with users generate an enormous amount of data.
Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation
Unpaired Image-to-Image Translation (I2IT) tasks often suffer from lack of data, a problem which self-supervised learning (SSL) has recently been very popular and successful at tackling.
