Thomas Savage

tsavage68's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a paper 6 days ago

SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration

Paper • 2411.10958 • Published 14 days ago • 47

updated 19 models 2 months ago

tsavage68/IE_L3_350steps_1e8rate_03beta_cSFTDPO

Text Generation • Updated Sep 24 • 8

tsavage68/IE_L3_450steps_1e8rate_01beta_cSFTDPO

Text Generation • Updated Sep 24 • 10

tsavage68/IE_L3_100steps_1e7rate_05beta_cSFTDPO

Text Generation • Updated Sep 24 • 10

tsavage68/IE_L3_100steps_1e7rate_03beta_cSFTDPO

Text Generation • Updated Sep 24 • 8

tsavage68/IE_L3_150steps_1e7rate_01beta_cSFTDPO

Text Generation • Updated Sep 24 • 9

tsavage68/IE_L3_1000steps_1e8rate_05beta_cSFTDPO

Text Generation • Updated Sep 24 • 8

tsavage68/IE_L3_1000steps_1e8rate_03beta_cSFTDPO

Text Generation • Updated Sep 24 • 9

tsavage68/IE_M2_350steps_1e8rate_05beta_cSFTDPO

Text Generation • Updated Sep 23 • 8

tsavage68/IE_L3_1000steps_1e8rate_01beta_cSFTDPO

Text Generation • Updated Sep 23 • 8

tsavage68/IE_M2_350steps_1e8rate_03beta_cSFTDPO

Text Generation • Updated Sep 23 • 11

tsavage68/IE_M2_350steps_1e8rate_01beta_cSFTDPO

Text Generation • Updated Sep 23 • 8

tsavage68/IE_M2_50steps_1e7rate_03beta_SFT

Text Generation • Updated Sep 23 • 8

tsavage68/IE_L3_1000steps_1e7rate_05beta_cSFTDPO

Text Generation • Updated Sep 23 • 8

tsavage68/IE_M2_100steps_1e7rate_01beta_cSFTDPO

Text Generation • Updated Sep 23 • 8

tsavage68/IE_M2_1000steps_1e8rate_05beta_cSFTDPO

Text Generation • Updated Sep 23 • 9

tsavage68/IE_L3_1000steps_1e7rate_03beta_cSFTDPO

Text Generation • Updated Sep 23 • 8

tsavage68/IE_M2_1000steps_1e8rate_03beta_cSFTDPO

Text Generation • Updated Sep 23 • 8

tsavage68/IE_L3_1000steps_1e7rate_01beta_cSFTDPO

Text Generation • Updated Sep 23 • 8

tsavage68/IE_M2_1000steps_1e8rate_01beta_cSFTDPO

Text Generation • Updated Sep 23 • 8