tsavage68/IE_L3_350steps_1e8rate_03beta_cSFTDPO
Text Generation
•
Updated
•
20
Thomas Savage
tsavage68
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
SageAttention2 Technical Report: Accurate 4 Bit Attention for
Plug-and-play Inference Acceleration
Organizations
None yet
models
512
tsavage68/IE_L3_450steps_1e8rate_01beta_cSFTDPO
Text Generation
•
Updated
•
16
tsavage68/IE_L3_100steps_1e7rate_05beta_cSFTDPO
Text Generation
•
Updated
•
16
tsavage68/IE_L3_100steps_1e7rate_03beta_cSFTDPO
Text Generation
•
Updated
•
18
tsavage68/IE_L3_150steps_1e7rate_01beta_cSFTDPO
Text Generation
•
Updated
•
14
tsavage68/IE_L3_1000steps_1e8rate_05beta_cSFTDPO
Text Generation
•
Updated
•
13
tsavage68/IE_L3_1000steps_1e8rate_03beta_cSFTDPO
Text Generation
•
Updated
•
16
tsavage68/IE_M2_350steps_1e8rate_05beta_cSFTDPO
Text Generation
•
Updated
•
15
tsavage68/IE_L3_1000steps_1e8rate_01beta_cSFTDPO
Text Generation
•
Updated
•
16
tsavage68/IE_M2_350steps_1e8rate_03beta_cSFTDPO
Text Generation
•
Updated
•
14
datasets
None public yet