Picture for Zhaoye Fei

Zhaoye Fei

InternLM2 Technical Report

Add code
Mar 26, 2024
Figure 1 for InternLM2 Technical Report
Figure 2 for InternLM2 Technical Report
Figure 3 for InternLM2 Technical Report
Figure 4 for InternLM2 Technical Report
Viaarxiv icon

WanJuan-CC: A Safe and High-Quality Open-sourced English Webtext Dataset

Add code
Mar 12, 2024
Figure 1 for WanJuan-CC: A Safe and High-Quality Open-sourced English Webtext Dataset
Figure 2 for WanJuan-CC: A Safe and High-Quality Open-sourced English Webtext Dataset
Figure 3 for WanJuan-CC: A Safe and High-Quality Open-sourced English Webtext Dataset
Figure 4 for WanJuan-CC: A Safe and High-Quality Open-sourced English Webtext Dataset
Viaarxiv icon

Balanced Data Sampling for Language Model Training with Clustering

Feb 22, 2024
Figure 1 for Balanced Data Sampling for Language Model Training with Clustering
Figure 2 for Balanced Data Sampling for Language Model Training with Clustering
Figure 3 for Balanced Data Sampling for Language Model Training with Clustering
Figure 4 for Balanced Data Sampling for Language Model Training with Clustering
Viaarxiv icon

Turn Waste into Worth: Rectifying Top-$k$ Router of MoE

Feb 21, 2024
Viaarxiv icon

InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning

Add code
Feb 09, 2024
Viaarxiv icon

Query of CC: Unearthing Large Scale Domain-Specific Knowledge from Public Corpora

Add code
Jan 26, 2024
Viaarxiv icon

Pre-training for Information Retrieval: Are Hyperlinks Fully Explored?

Add code
Sep 14, 2022
Figure 1 for Pre-training for Information Retrieval: Are Hyperlinks Fully Explored?
Figure 2 for Pre-training for Information Retrieval: Are Hyperlinks Fully Explored?
Figure 3 for Pre-training for Information Retrieval: Are Hyperlinks Fully Explored?
Figure 4 for Pre-training for Information Retrieval: Are Hyperlinks Fully Explored?
Viaarxiv icon

Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding

Aug 19, 2022
Figure 1 for Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding
Figure 2 for Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding
Figure 3 for Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding
Figure 4 for Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding
Viaarxiv icon

Towards More Effective and Economic Sparsely-Activated Model

Oct 14, 2021
Figure 1 for Towards More Effective and Economic Sparsely-Activated Model
Figure 2 for Towards More Effective and Economic Sparsely-Activated Model
Figure 3 for Towards More Effective and Economic Sparsely-Activated Model
Figure 4 for Towards More Effective and Economic Sparsely-Activated Model
Viaarxiv icon