·
AI & ML interests
None yet
Organizations
zhangify/smollm2-1.7B-sft
Updated
zhangify/adamw_lr1e-5-merged-step100
Updated
zhangify/ddp-omi-llama3b-lorafull-precondadamw-lr5e-5linear
4B • Updated • 1
zhangify/ddp-omi-llama3b-lorafull-precondadamw-lr2e-5linear
4B • Updated • 1
zhangify/ddp-omi-llama3b-lorafull-precondadamw-lr2e-4linear
4B • Updated • 1
zhangify/ddp-omi-llama3b-lorafull-precondadamw-lr1e-4linear
4B • Updated • 1
zhangify/ddp-omi-llama3b-lorafull-adamw-lr5e-5linear
4B • Updated • 1
zhangify/ddp-omi-llama3b-lorafull-adamw-lr2e-5linear
4B • Updated • 1
zhangify/ddp-omi-llama3b-lorafull-adamw-lr2e-4linear
4B • Updated • 1
zhangify/ddp-omi-llama3b-lorafull-adamw-lr1e-4linear
4B • Updated • 1
zhangify/ddp-llama3b-lorafull-precondadamw-lr6e-4
4B • Updated zhangify/ddp-llama3b-lorafull-precondadamw-lr3e-5
4B • Updated zhangify/ddp-llama3b-lorafull-precondadamw-lr3e-4
4B • Updated zhangify/ddp-llama3b-lorafull-precondadamw-lr1.5e-4
4B • Updated zhangify/ddp-llama3b-lorafull-adamw-lr6e-4
4B • Updated zhangify/ddp-llama3b-lorafull-adamw-lr3e-5
4B • Updated zhangify/ddp-llama3b-lorafull-adamw-lr3e-4
4B • Updated zhangify/ddp-llama3b-lorafull-adamw-lr1.5e-4
4B • Updated zhangify/llama3b-lorafull-precondadamw-approx_rank1-lr2e-4
4B • Updated zhangify/llama3b-lorafull-precondadamw-approx_rank1-lr1e-4
4B • Updated zhangify/llama3b-lorafull-precondadamw-approx_rank1-lr5e-5
4B • Updated zhangify/llama3b-lorafull-precondadamw-approx_rank1
4B • Updated zhangify/omi-llama3b-lorafull-precondadamw-lr5e-5linear-r256
zhangify/omi-llama3b-lorafull-precondadamw-lr2e-4linear-r256
zhangify/omi-llama3b-lorafull-precondadamw-lr1e-5linear-r256
4B • Updated • 1
zhangify/omi-llama3b-lorafull-precondadamw-lr1e-4linear-r256
4B • Updated • 1
zhangify/omi-llama3b-lorafull-adamw-lr5e-5linear-r256
4B • Updated • 1
zhangify/omi-llama3b-lorafull-adamw-lr2e-4linear-r256
4B • Updated • 1
zhangify/omi-llama3b-lorafull-adamw-lr1e-5linear-r256
4B • Updated • 1
zhangify/omi-llama3b-lorafull-adamw-lr1e-4linear-r256
4B • Updated • 1