Submissions from gilesthomas.com

		Poppy the training box, part 1: The beginnings (gilesthomas.com)
		3 points by ibobev 10 days ago \| past \| discuss
		Building intuition about LLM parameter counts (gilesthomas.com)
		3 points by ibobev 10 days ago \| past \| discuss
		Building intuition about LLM parameter counts (gilesthomas.com)
		2 points by gpjt 13 days ago \| past \| discuss
		Poppy the training box, part 1: the beginnings (gilesthomas.com)
		3 points by gpjt 15 days ago \| past
		From bigrams to GPT-2, one component at a time (in Jax) (gilesthomas.com)
		1 point by gpjt 15 days ago \| past
		Building a Jax training loop for an LLM training run (gilesthomas.com)
		2 points by gpjt 23 days ago \| past
		Thoughts on Role Confusion (gilesthomas.com)
		2 points by ibobev 28 days ago \| past
		Thoughts on Role Confusion (gilesthomas.com)
		3 points by gpjt 29 days ago \| past
		Flax debugging: making a hash of things (gilesthomas.com)
		3 points by ibobev 36 days ago \| past
		Flax debugging: making a hash of things (gilesthomas.com)
		2 points by gpjt 36 days ago \| past
		10Gb/s Ethernet: switching to a Broadcom SFP+ module (gilesthomas.com)
		195 points by gpjt 37 days ago \| past \| 170 comments
		Jax: Commitment Issues (gilesthomas.com)
		3 points by ibobev 37 days ago \| past
		Jax: Commitment Issues (gilesthomas.com)
		4 points by gpjt 38 days ago \| past
		Jax Back Ends and Devices (gilesthomas.com)
		2 points by ibobev 46 days ago \| past
		Jax Back Ends and Devices (gilesthomas.com)
		2 points by gpjt 48 days ago \| past
		Using Safetensors with Flax (gilesthomas.com)
		1 point by ibobev 48 days ago \| past
		Using Safetensors with Flax (gilesthomas.com)
		2 points by gpjt 49 days ago \| past
		First Looking into Jax (gilesthomas.com)
		2 points by ibobev 52 days ago \| past
		First Looking into Jax (gilesthomas.com)
		3 points by gpjt 54 days ago \| past
		10Gb/s Ethernet: using mini-heatsinks with a 10GBASE-T SFP+ module (gilesthomas.com)
		1 point by ibobev 65 days ago \| past
		10Gb/s Ethernet: using mini-heatsinks with a 10GBASE-T SFP+ module (gilesthomas.com)
		3 points by gpjt 66 days ago \| past
		10Gb/s Ethernet: what I did to get it working in my home (gilesthomas.com)
		232 points by gpjt 85 days ago \| past \| 177 comments
		10Gb Ethernet: what I had to (re)learn (gilesthomas.com)
		2 points by ibobev 85 days ago \| past
		10Gb Ethernet: what I had to (re)learn (gilesthomas.com)
		1 point by gpjt 86 days ago \| past \| 1 comment
		LLM from scratch, part 33 – what I learned from the appendices (gilesthomas.com)
		5 points by gpjt 3 months ago \| past
		LLM from scratch (32l) – Interventions: updated instruction fine-tuning results (gilesthomas.com)
		1 point by gpjt 3 months ago \| past
		An LLM becomes more coherent as we train it (gilesthomas.com)
		1 point by ibobev 3 months ago \| past
		How an LLM becomes more coherent as we train it (gilesthomas.com)
		3 points by gpjt 3 months ago \| past
		LLM from scratch, part 32k – Interventions: gradient accumulation (gilesthomas.com)
		2 points by gpjt 3 months ago \| past
		Interventions: Trying to train a better model in the cloud (gilesthomas.com)
		1 point by ibobev 3 months ago \| past
		More