gpjt on Hugging Face: downloads and rankings
gpjt has 55 tracked models, downloaded 6,402 times in the last 30 days and 17,621 times in total; 8 datasets, downloaded 541 times in the last 30 days. gpjt Wrapped: the last 12 months.
Models by downloads in the last 30 days
- gpjt/jax-with-mha-bias-fw-fwedu-simplewiki 826 downloads, text generation
- gpjt/jax-with-mha-bias-fw-fwedu-simplewiki-DEPRECATED 825 downloads, text generation
- gpjt/jax-with-mha-bias-fw-fwedu-5050 447 downloads, text generation
- gpjt/jax-with-mha-bias-fw-fwedu-5050-DEPRECATED 440 downloads, text generation
- gpjt/1xrtx3090-moe-1 369 downloads, text generation
- gpjt/jax-with-mha-bias-fineweb-edu 325 downloads, text generation
- gpjt/8xa100m40-baseline 253 downloads, text generation
- gpjt/jax-with-mha-bias-openwebtext 241 downloads, text generation
- gpjt/8xa100m40-lore-9-new-seed-output-only 155 downloads, text generation
- gpjt/8xa100m40-lore-8-new-seed-both-smart-init 151 downloads, text generation
- gpjt/8xa100m40-lore-3-both-smart-init 145 downloads, text generation
- gpjt/8xa100m40-lore-7-new-seed-input-only 145 downloads, text generation
- gpjt/8xa100m40-lore-6-new-seed-baseline-disabled 141 downloads, text generation
- gpjt/8xa100m40-lore-4-input-only 141 downloads, text generation
- gpjt/8xa100m40-lore-5-output-only 140 downloads, text generation
- gpjt/8xa100m40-lore-2-both-ordinary-init 139 downloads, text generation
- gpjt/8xa100m40-lore-11-output-only-corrected-smart-init 128 downloads, text generation
- gpjt/8xa100m40-lore-10-both-corrected-smart-init 121 downloads, text generation
- gpjt/8xa100m40-lore-1-baseline-disabled 120 downloads, text generation
- gpjt/jax-no-mha-bias-no-dropout 114 downloads, text generation
- gpjt/jax-with-mha-bias-no-dropout-extended 105 downloads, text generation
- gpjt/jax-with-mha-bias-larger-chinchilla-1 105 downloads, text generation
- gpjt/jax-with-mha-bias-larger-chinchilla-2 100 downloads, text generation
- gpjt/jax-with-mha-bias-no-dropout 95 downloads, text generation
- gpjt/jax-with-mha-bias-no-dropout-2-epoch 94 downloads, text generation
- gpjt/jax-no-mha-bias-with-dropout 94 downloads, text generation
- gpjt/8xa100m40-baseline-5 24 downloads, text generation
- gpjt/8xa100m40-stacked-interventions-2 24 downloads, text generation
- gpjt/8xa100m80 20 downloads, text generation
- gpjt/8xh100m80-best 19 downloads, text generation
- gpjt/Meta-Llama-3-8B-openassistant-guanaco-llama2-format 18 downloads, text generation
- gpjt/8xa100m40-baseline-6 18 downloads, text generation
- gpjt/8xb200m160 18 downloads, text generation
- gpjt/8xa100m40-baseline-2 17 downloads, text generation
- gpjt/8xa100m40-stacked-interventions-1 16 downloads, text generation
- gpjt/8xh100m80-latest 16 downloads, text generation
- gpjt/1xrtx3090m24-fineweb-edu-2x 16 downloads, text generation
- gpjt/8xa100m40-gradient-clipping 16 downloads, text generation
- gpjt/8xa100m40-qkv-bias 16 downloads, text generation
- gpjt/8xa100m40-stacked-interventions-3 15 downloads, text generation
- gpjt/8xa100m40-weight-decay-cerebras 15 downloads, text generation
- gpjt/8xa100m40-baseline-8 15 downloads, text generation
- gpjt/8xa100m40-weight-decay-gpt2 14 downloads, text generation
- gpjt/8xa100m40 14 downloads, text generation
- gpjt/Qwen1.5-0.5B-openassistant-guanaco-llama2-format 14 downloads, text generation
- gpjt/1xrtx3090m24-fineweb-edu 13 downloads, text generation
- gpjt/8xa100m40-baseline-3 13 downloads, text generation
- gpjt/8xa100m40-schedule-learning-rate 13 downloads, text generation
- gpjt/1xrtx3090-stacked-interventions 13 downloads, text generation
- gpjt/1xrtx3090-baseline 13 downloads, text generation
- gpjt/8xa100m40-baseline-7 12 downloads, text generation
- gpjt/8xa100m40-remove-dropout 12 downloads, text generation
- gpjt/1xrtx3090m24-fineweb 11 downloads, text generation
- gpjt/8xa100m80-no-amp 9 downloads, text generation
- gpjt/8xa100m40-baseline-4 9 downloads, text generation
Datasets by downloads in the last 30 days
- gpjt/fineweb-gpt2-tokens 112 downloads
- gpjt/fw-fwedu-5050-gpt2-tokens 90 downloads
- gpjt/fw-fwedu-simplewiki-gpt2-tokens 74 downloads
- gpjt/fw-fwedu-5050-gpt2-tokens-DEPRECATED 67 downloads
- gpjt/fw-fwedu-simplewiki-gpt2-tokens-DEPRECATED 60 downloads
- gpjt/fineweb-edu-gpt2-tokens 53 downloads
- gpjt/openwebtext-gpt2-tokens-DEPRECATED 52 downloads
- gpjt/openassistant-guanaco-llama2-format 33 downloads