←back to thread

Apertus 70B: Truly Open - Swiss LLM by ETH, EPFL and CSCS

(huggingface.co)
321 points denysvitali | 1 comments | 02 Sep 25 20:14 UTC | HN request time: 0s | source
Show context
tarruda ◴[05 Sep 25 21:26 UTC] No.45143820[source]▶
Is there any practical method to verify that the model was trained from the reported dataset?
replies(1): >>45143950 #
1. lllllm ◴[05 Sep 25 21:39 UTC] No.45143950[source]▶
we released 81 intermediate checkpoints of the whole pretraining phase, and the code and data to reproduce. so full audit is surely possible - still it would depend on what you consider 'practical' here.