Picture for Shrimai Prabhumoye

Shrimai Prabhumoye

Data, Data Everywhere: A Guide for Pretraining Dataset Construction

Add code
Jul 08, 2024
Viaarxiv icon

Nemotron-4 340B Technical Report

Add code
Jun 17, 2024
Figure 1 for Nemotron-4 340B Technical Report
Figure 2 for Nemotron-4 340B Technical Report
Figure 3 for Nemotron-4 340B Technical Report
Figure 4 for Nemotron-4 340B Technical Report
Viaarxiv icon

AgentKit: Flow Engineering with Graphs, not Coding

Add code
Apr 17, 2024
Figure 1 for AgentKit: Flow Engineering with Graphs, not Coding
Figure 2 for AgentKit: Flow Engineering with Graphs, not Coding
Figure 3 for AgentKit: Flow Engineering with Graphs, not Coding
Figure 4 for AgentKit: Flow Engineering with Graphs, not Coding
Viaarxiv icon

Nemotron-4 15B Technical Report

Add code
Feb 27, 2024
Figure 1 for Nemotron-4 15B Technical Report
Figure 2 for Nemotron-4 15B Technical Report
Figure 3 for Nemotron-4 15B Technical Report
Figure 4 for Nemotron-4 15B Technical Report
Viaarxiv icon

SPRING: GPT-4 Out-performs RL Algorithms by Studying Papers and Reasoning

Add code
May 24, 2023
Figure 1 for SPRING: GPT-4 Out-performs RL Algorithms by Studying Papers and Reasoning
Figure 2 for SPRING: GPT-4 Out-performs RL Algorithms by Studying Papers and Reasoning
Figure 3 for SPRING: GPT-4 Out-performs RL Algorithms by Studying Papers and Reasoning
Figure 4 for SPRING: GPT-4 Out-performs RL Algorithms by Studying Papers and Reasoning
Viaarxiv icon

Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents

Add code
May 07, 2023
Figure 1 for Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents
Figure 2 for Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents
Figure 3 for Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents
Figure 4 for Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents
Viaarxiv icon

Self-Refine: Iterative Refinement with Self-Feedback

Add code
Mar 30, 2023
Figure 1 for Self-Refine: Iterative Refinement with Self-Feedback
Figure 2 for Self-Refine: Iterative Refinement with Self-Feedback
Figure 3 for Self-Refine: Iterative Refinement with Self-Feedback
Figure 4 for Self-Refine: Iterative Refinement with Self-Feedback
Viaarxiv icon

Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models

Add code
Feb 14, 2023
Figure 1 for Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models
Figure 2 for Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models
Figure 3 for Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models
Figure 4 for Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models
Viaarxiv icon

AutoBiasTest: Controllable Sentence Generation for Automated and Open-Ended Social Bias Testing in Language Models

Add code
Feb 14, 2023
Figure 1 for AutoBiasTest: Controllable Sentence Generation for Automated and Open-Ended Social Bias Testing in Language Models
Figure 2 for AutoBiasTest: Controllable Sentence Generation for Automated and Open-Ended Social Bias Testing in Language Models
Figure 3 for AutoBiasTest: Controllable Sentence Generation for Automated and Open-Ended Social Bias Testing in Language Models
Figure 4 for AutoBiasTest: Controllable Sentence Generation for Automated and Open-Ended Social Bias Testing in Language Models
Viaarxiv icon

Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions

Add code
Nov 21, 2022
Figure 1 for Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions
Figure 2 for Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions
Figure 3 for Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions
Figure 4 for Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions
Viaarxiv icon