gpjt
- Karma
- 1,714
- Created
- 17 years ago
About
https://www.gilesthomas.com/Recent Submissions
- 1. ▲ 10Gb/s Ethernet: what I did to get it working in my home (gilesthomas.com)
- 2. ▲ 10Gb Ethernet: what I had to (re)learn (gilesthomas.com)
- 3. ▲ LLM from scratch, part 33 – what I learned from the appendices (gilesthomas.com)
- 4. ▲ LLM from scratch (32l) – Interventions: updated instruction fine-tuning results (gilesthomas.com)
- 5. ▲ How an LLM becomes more coherent as we train it (gilesthomas.com)
- 6. ▲ LLM from scratch, part 32k – Interventions: gradient accumulation (gilesthomas.com)
- 7. ▲ Provision: LLM-powered server setup from Markdown (provision.sh)
- 8. ▲ LLM from scratch, part 32j – trying to train a better model in the cloud (gilesthomas.com)
- 9. ▲ Writing an LLM from scratch, part 32i – Interventions: what is in the noise? (gilesthomas.com)
- 10. ▲ Writing an LLM from scratch, part 32h – Interventions: full fat float32 (gilesthomas.com)