Models and Datasets of paper: [Simplified Sparse Attention via Gist Tokens]
Yuzhen Mao
gist-sparse-attention
·
AI & ML interests
None yet
Recent Activity
commentedon a paper about 1 month ago
Simplified Sparse Attention via Gist Tokens commentedon a paper about 1 month ago
Simplified Sparse Attention via Gist Tokens upvoted a paper 4 months ago
Simplified Sparse Attention via Gist TokensOrganizations
models 19
gist-sparse-attention/GSA-FT-Qwen2-7B-Instruct-chunk8
333k • Updated • 8
gist-sparse-attention/GSA-FT-Qwen2-7B-Instruct-chunk16
333k • Updated • 14
gist-sparse-attention/GSA-FT-Qwen2-7B-Instruct-chunk32
333k • Updated • 14
gist-sparse-attention/GSA-FT-Qwen2-7B-Instruct-chunk4-chunk4
333k • Updated • 418
gist-sparse-attention/GSA-FT-Qwen2-7B-Instruct-chunk8-chunk4
333k • Updated • 24
gist-sparse-attention/GSA-FT-Llama-3.2-1B-chunk16
1B • Updated • 71
gist-sparse-attention/GSA-FT-Llama-3.2-1B-chunk4-chunk4
1B • Updated • 42
gist-sparse-attention/GSA-link-FT-Llama-3.2-1B-chunk8
1B • Updated • 11
gist-sparse-attention/GSA-link-FT-Llama-3.2-1B-chunk16
1B • Updated • 18
gist-sparse-attention/GSA-link-FT-Llama-3.2-1B-chunk4-chunk4
1B • Updated • 11
datasets 14
gist-sparse-attention/GSA-FT-Llama-3.2-1B-data
Preview • Updated • 75
gist-sparse-attention/GSA-FT-Qwen2-7B-Instruct-chunk8-chunk4-data
Preview • Updated • 335
gist-sparse-attention/GSA-FT-Qwen2-7B-Instruct-chunk4-chunk4-data
Preview • Updated • 108
gist-sparse-attention/GSA-FT-Qwen2-7B-Instruct-chunk32-data
Viewer • Updated • 25.9k • 199
gist-sparse-attention/GSA-FT-Qwen2-7B-Instruct-chunk16-data
Preview • Updated • 200
gist-sparse-attention/GSA-FT-Qwen2-7B-Instruct-chunk8-data
Preview • Updated • 49
gist-sparse-attention/GSA-PT-Qwen2-7B-Instruct-chunk8-chunk4-data
Viewer • Updated • 88.6k • 187
gist-sparse-attention/GSA-PT-Qwen2-7B-Instruct-chunk4-chunk4-data
Viewer • Updated • 88.5k • 176
gist-sparse-attention/GSA-PT-Qwen2-7B-Instruct-chunk32-data
Preview • Updated • 290
gist-sparse-attention/GSA-PT-Qwen2-7B-Instruct-chunk16-data
Viewer • Updated • 88.8k • 326