← sources

HN: We fine-tuned a 235B model on 4 GPUs. Then we didn't need it

source: hackernewspublished 2026-10-19 12:35ingested 2026-10-24 13:27

retained text

Points: 14 | Comments: 2
Author: kgritesh
Link: https://blog.vertexcover.io/fine-tuning-235b-moe-four-gpus
We fine-tuned a 235B model on 4 GPUs. Then we didn't need it

document fetched 2026-10-26 02:54