gpjt/1xrtx3090-stacked-interventions
Text Generation • 0.2B • Updated • 292
Giles Thomas
gpjt
AI & ML interests
Doing my best to speedrun 20 years of AI research. YMMV
Recent Activity
updated a collection 1 day ago
LLM from scratch updated a model 1 day ago
gpjt/1xrtx3090-stacked-interventions published a model 1 day ago
gpjt/1xrtx3090-stacked-interventionsOrganizations
None yet
gpjt/1xrtx3090-baseline
Text Generation • 0.2B • Updated • 199
gpjt/8xa100m40-stacked-interventions-3
Text Generation • 0.2B • Updated • 191
gpjt/8xa100m40-stacked-interventions-2
Text Generation • 0.2B • Updated • 248
gpjt/8xa100m40-stacked-interventions-1
Text Generation • 0.2B • Updated • 239
gpjt/8xa100m40-baseline-8
Text Generation • 0.2B • Updated • 508
gpjt/8xa100m40-baseline-7
Text Generation • 0.2B • Updated • 507
gpjt/8xa100m40-baseline-6
Text Generation • 0.2B • Updated • 496
gpjt/8xa100m40-baseline-4
Text Generation • 0.2B • Updated • 310
gpjt/8xa100m40-baseline-5
Text Generation • 0.2B • Updated • 492
gpjt/8xa100m40-baseline-3
Text Generation • 0.2B • Updated • 558
gpjt/8xa100m40-baseline-2
Text Generation • 0.2B • Updated • 519
gpjt/8xa100m80-no-amp
Text Generation • 0.2B • Updated • 248
gpjt/8xa100m40-weight-decay-cerebras
Text Generation • 0.2B • Updated • 350
gpjt/8xa100m40-weight-decay-gpt2
Text Generation • 0.2B • Updated • 336
gpjt/8xa100m40-qkv-bias
Text Generation • 0.2B • Updated • 82
gpjt/8xa100m40-schedule-learning-rate
Text Generation • 0.2B • Updated • 81
gpjt/8xa100m40-remove-dropout
Text Generation • 0.2B • Updated • 86
gpjt/8xa100m40-baseline
Text Generation • 0.2B • Updated • 81
gpjt/1xrtx3090m24-fineweb-edu-2x
Text Generation • 0.2B • Updated • 75
gpjt/1xrtx3090m24-fineweb-edu
Text Generation • 0.2B • Updated • 77
gpjt/1xrtx3090m24-fineweb
Text Generation • 0.2B • Updated • 83
gpjt/8xh100m80-latest
Text Generation • 0.2B • Updated • 76
gpjt/8xh100m80-best
Text Generation • 0.2B • Updated • 79
gpjt/8xb200m160
Text Generation • 0.2B • Updated • 85
gpjt/8xa100m80
Text Generation • 0.2B • Updated • 81
gpjt/8xa100m40
Text Generation • 0.2B • Updated • 117
gpjt/8xa100m40-gradient-clipping
Text Generation • 0.2B • Updated • 77
gpjt/test5
Text Generation • 0.2B • Updated • 7
gpjt/test4
Text Generation • 0.2B • Updated • 3