smcleish/050926-06B4B-d64-s16-sp2-local-softmax-from-hf-lora-fineweb-edu-2838k Updated about 13 hours ago
smcleish/050926-06B4B-d64-s8-sp2-local-softmax-from-hf-lora-fineweb-edu-2838k Updated about 14 hours ago
smcleish/050926-06B4B-d64-s16-sp2-local-softmax-from-hf-lora-nemotron-math-2838k Updated about 15 hours ago
smcleish/050926-06B4B-d64-s8-sp2-local-softmax-from-hf-lora-nemotron-math-2838k Updated about 16 hours ago
smcleish/050926-06B4B-d64-s16-sp2-local-softmax-from-hf-lora-nemotron-cc-2838k Updated about 16 hours ago
smcleish/050926-06B4B-d64-s8-sp2-local-softmax-from-hf-lora-nemotron-cc-2838k Updated about 19 hours ago
smcleish/120726-06B-latent06B-4B-d64-s8-stage2-from-stage1-cosine-latent-causal-noise60-frozen-encdec Updated Jul 21
smcleish/120726-06B-latent06B-4B-d64-s8-stage2-from-stage1-cosine-latent-causal-noise45-frozen-encdec Updated Jul 21
smcleish/120726-06B-latent06B-4B-d64-s8-stage2-from-stage1-cosine-latent-causal-noise5-frozen-encdec Updated Jul 20