The Super Weight in Large Language Models · HackerPapers discussions

The Super Weight in Large Language Models — HN submission

Tue, 05 Aug 2025 00:56:28 GMT

The Super Weight in Large Language Models

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Super Weight in Large Language Models — HN submission

Mon, 04 Aug 2025 15:19:11 GMT

The Super Weight in Large Language Models

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Super Weight in Large Language Models — mentioned by kouteiheika

Fri, 30 May 2025 15:20:15 GMT

> The number of quantized bits is a trade off between size and quality. Ideally you should be aiming for a 6-bit or 5-bit model. I've seen some models be unstable at 4-bit (where they will either repeat words or start generating random words). Note that that's a skill issue of whoever quantized the model. In general quantization even as low as 3-bit can be almost loseless when you do quantization-aware finetuning[1] (and apparently you don't even need that many training tokens), but even if you don't want to do any extra training you can be smart as to which parts of the model you're…

Paper and discussion history. A mention is not an endorsement.

The Super Weight in Large Language Models — HN submission

Wed, 27 Nov 2024 20:27:20 GMT

Pruning a single weight in an LLM can destroy its output

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Super Weight in Large Language Models — HN submission

Tue, 12 Nov 2024 11:15:11 GMT

The Super Weight in Large Language Models

6 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.