The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction — mentioned by column

Thu, 25 Jan 2024 15:31:53 GMT

I kind of disagree. It's not "user friendly" but it is very descriptive. They are codenames afterall. Take "dolphin-2.6-mistral-7b-dpo-laser" for instance : with a little LLM background knowledge, just from the name you know it is a 7 billion parameters model based on Mistral, with a filtered dataset to remove alignment and bias (dolphin), version 2.6 and using the techniques described in the Direct Preference Optimization (https://arxiv.org/pdf/2305.18290.pdf) and Laser (https://arxiv.org/pdf/2312.13558.pdf) papers to improve its output.

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

The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction — HN submission

Sat, 06 Jan 2024 17:32:16 GMT

Improving Reasoning in Language Models with Layer-Selective Rank Reduction

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

The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction · HackerPapers discussions

The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction — mentioned by column

The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction — HN submission