gpjt/1xrtx3090-stacked-interventions
Text Generation • 0.2B • Updated • 331
Giles Thomas
gpjt
AI & ML interests
Doing my best to speedrun 20 years of AI research. YMMV
Recent Activity
updated a collection 23 days ago
LLM from scratch updated a model 23 days ago
gpjt/1xrtx3090-stacked-interventions published a model 23 days ago
gpjt/1xrtx3090-stacked-interventionsOrganizations
None yet
gpjt/1xrtx3090-baseline
Text Generation • 0.2B • Updated • 234
gpjt/8xa100m40-stacked-interventions-3
Text Generation • 0.2B • Updated • 226
gpjt/8xa100m40-stacked-interventions-2
Text Generation • 0.2B • Updated • 248
gpjt/8xa100m40-stacked-interventions-1
Text Generation • 0.2B • Updated • 141
gpjt/8xa100m40-baseline-8
Text Generation • 0.2B • Updated • 140
gpjt/8xa100m40-baseline-7
Text Generation • 0.2B • Updated • 143
gpjt/8xa100m40-baseline-6
Text Generation • 0.2B • Updated • 145
gpjt/8xa100m40-baseline-4
Text Generation • 0.2B • Updated • 131
gpjt/8xa100m40-baseline-5
Text Generation • 0.2B • Updated • 138
gpjt/8xa100m40-baseline-3
Text Generation • 0.2B • Updated • 142
gpjt/8xa100m40-baseline-2
Text Generation • 0.2B • Updated • 131
gpjt/8xa100m80-no-amp
Text Generation • 0.2B • Updated • 34
gpjt/8xa100m40-weight-decay-cerebras
Text Generation • 0.2B • Updated • 41
gpjt/8xa100m40-weight-decay-gpt2
Text Generation • 0.2B • Updated • 35
gpjt/8xa100m40-qkv-bias
Text Generation • 0.2B • Updated • 35
gpjt/8xa100m40-schedule-learning-rate
Text Generation • 0.2B • Updated • 36
gpjt/8xa100m40-remove-dropout
Text Generation • 0.2B • Updated • 35
gpjt/8xa100m40-baseline
Text Generation • 0.2B • Updated • 35
gpjt/1xrtx3090m24-fineweb-edu-2x
Text Generation • 0.2B • Updated • 40
gpjt/1xrtx3090m24-fineweb-edu
Text Generation • 0.2B • Updated • 35
gpjt/1xrtx3090m24-fineweb
Text Generation • 0.2B • Updated • 36
gpjt/8xh100m80-latest
Text Generation • 0.2B • Updated • 34
gpjt/8xh100m80-best
Text Generation • 0.2B • Updated • 40
gpjt/8xb200m160
Text Generation • 0.2B • Updated • 44
gpjt/8xa100m80
Text Generation • 0.2B • Updated • 39
gpjt/8xa100m40
Text Generation • 0.2B • Updated • 75
gpjt/8xa100m40-gradient-clipping
Text Generation • 0.2B • Updated • 37
gpjt/test5
Text Generation • 0.2B • Updated • 7
gpjt/test4
Text Generation • 0.2B • Updated • 6