newmindai/Llama-3.1-8B-Instruct-w16a16-tw
Text Generation
•
8B
•
Updated
•
99
Precision Labs
FP8 Rowwise and BF16 tensorwise models with optimized recipes for large-scale training efficiency and convergence stability.
-
-
newmindai/Llama-3.1-8B-Instruct-w16a8-rw
Text Generation • 8B • Updated • 96 -
newmindai/Llama-3.1-8B-Instruct_w16a8_rw_with_gw_hp
Text Generation • 8B • Updated • 86 -
newmindai/Llama-3.1-8B-Instruct-w16a8-mxtw
Text Generation • 8B • Updated • 88 -
newmindai/Llama-3.1-8B-Instruct-w16a8-1node-bs8
Text Generation • 8B • Updated • 84 -
newmindai/Llama-3.1-8B-Instruct-w16a16-4nodes-bs32
Text Generation • 8B • Updated • 88 -
newmindai/Llama-3.1-8B-Instruct-w16a8-4nodes-bs32
Text Generation • 8B • Updated • 59 -
newmindai/Llama-3.1-8B-Instruct-w16a8-8nodes-bs64
Text Generation • 8B • Updated • 32 -
newmindai/Llama-3.1-8B-Instruct-w16a8-4nodes-bs64
Text Generation • 8B • Updated • 32 -
newmindai/Llama-3.1-8B-Instruct-w16a16-8nodes-bs32
Text Generation • 8B • Updated • 67 -
newmindai/Llama-3.1-8B-Instruct-w16a8-8nodes-bs32
Text Generation • 8B • Updated • 65 -
newmindai/Llama-3.1-8B-Instruct-w16a8-rw-4nodes
Text Generation • 8B • Updated • 2 -
newmindai/Llama-3.1-8B-Instruct-w16a8-rw-8nodes
Text Generation • 8B • Updated • 2 -
newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes
Text Generation • Updated • 2 -
newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-8nodes
Text Generation • 8B • Updated • 5