FemtoGPT
AI
language model implementation
SHOW HN2023
19points
6comments
#1,721of 3,109 in 2023
Top 56%of 2023 by points
How HN took it
QuietFewer than 5 comments about the project
1 positive, 1 neutral or asking, 0 mixed, 1 critical, out of 3 comments about the project.
Idea: 1 for, 0 againstPerformance: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Good learning resource for Rust
From 2 comments
Well done! I would be crazy if I dived into this having never studied Rust! But it looks very interesting so I might do that! I have almost finished AK’s lecture. Have you made…
quickthrower2 on HNHey! Yes please dive in :) It can be a starting point for learning Rust ;) MatMul is fine, the bottleneck is LayerNorm + Softmax gradients right now. Haven't been able to…
keyvank on HN
Objections
Training is slow, about 3 seconds per step on one user's machine
From 2 comments
Well, first step is to run it. I am getting a step every 3 seconds. Is that typical? i7-13700H, 2400 Mhz, 14 Core(s), 20 Logical Processor(s). It is using 12 CPUs which is good.…
quickthrower2 on HNYes release. Is running on Windows which might affect things.
quickthrower2 on HN
Requests
Faster matrix multiplication
From 1 comment
Well done! I would be crazy if I dived into this having never studied Rust! But it looks very interesting so I might do that! I have almost finished AK’s lecture. Have you made…
quickthrower2 on HN
Questions
Whether the per-step speed is typical
From 1 comment
Well, first step is to run it. I am getting a step every 3 seconds. Is that typical? i7-13700H, 2400 Mhz, 14 Core(s), 20 Logical Processor(s). It is using 12 CPUs which is good.…
quickthrower2 on HN