Search: gilesthomas.com | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

The maths you need to start understanding LLMs (gilesthomas.com)

616 points

9 months ago

2.

LLM from scratch, part 28 – training a base model from scratch on an RTX 3090 (gilesthomas.com)

540 points

6 months ago

3.

Writing an LLM from scratch, part 8 – trainable self-attention (gilesthomas.com)

380 points

a year ago

4.

Writing an LLM from scratch, part 13 – attention heads are dumb (gilesthomas.com)

351 points

a year ago

5.

It’s still worth blogging in the age of AI (gilesthomas.com)

333 points

a year ago

6.

The benefits of learning in public (gilesthomas.com)

311 points

a year ago

7.

Writing an LLM from scratch, part 22 – training our LLM (gilesthomas.com)

254 points

8 months ago

8.

10Gb/s Ethernet: what I did to get it working in my home (gilesthomas.com)

232 points

a month ago

9.

Writing an LLM from scratch, part 10 – dropout (gilesthomas.com)

90 points

a year ago

10.

Writing an LLM from scratch, part 20 – starting training, and cross entropy loss (gilesthomas.com)

41 points

8 months ago

11.

Using DistributedDataParallel to train a base model from scratch in the cloud (gilesthomas.com)

10 points

5 months ago

12.

Writing an LLM from scratch, part 17 – the feed-forward network (gilesthomas.com)

8 points

10 months ago

13.

IT headhunters considered harmful (gilesthomas.com)

7 points

16 years ago

14.

Writing an LLM from scratch, part 32h – Interventions: full fat float32 (gilesthomas.com)

7 points

2 months ago

15.

Writing an LLM from scratch, part 15 – from context vectors to logits (gilesthomas.com)

7 points

a year ago

16.

Writing an LLM from scratch, part 32f – Interventions: weight decay (gilesthomas.com)

6 points

2 months ago

17.

Writing an LLM from scratch, part 32d – Interventions: adding attention bias (gilesthomas.com)

6 points

4 months ago

18.

LLM from scratch, part 33 – what I learned from the appendices (gilesthomas.com)

5 points

a month ago

19.

Pam-unshare: a PAM module that switches into a PID namespace (gilesthomas.com)

5 points

10 years ago

20.

Writing an LLM from scratch, part 26 – evaluating the fine-tuned model (gilesthomas.com)

4 points

7 months ago

21.

Writing an LLM from scratch, part 9 – causal attention (gilesthomas.com)

4 points

a year ago

22.

Does #EUVAT make charging Bitcoin impossible for EU digital services businesses? (gilesthomas.com)

3 points

11 years ago

23.

10Gb/s Ethernet: using mini-heatsinks with a 10GBASE-T SFP+ module (gilesthomas.com)

3 points

18 days ago

24.

How an LLM becomes more coherent as we train it (gilesthomas.com)

3 points

2 months ago

25.

Writing an LLM from scratch, part 32e – Interventions: the learning rate (gilesthomas.com)

3 points

3 months ago

26.

Writing an LLM from scratch, part 32e – Interventions: the learning rate (gilesthomas.com)

3 points

3 months ago

27.

Writing an LLM from scratch, part 32a – Interventions: training a baseline model (gilesthomas.com)

3 points

4 months ago

28.

Retro Language Models: Rebuilding Karpathy's RNN in PyTorch (gilesthomas.com)

3 points

7 months ago

29.

Leaving PythonAnywhere (gilesthomas.com)

3 points

a year ago

30.

Writing an LLM from scratch, part 12 – multi-head attention (gilesthomas.com)

3 points

a year ago