Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor · HackerPapers discussions

Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor — HN submission

Fri, 25 Aug 2023 09:05:03 GMT

Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor

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

Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor — mentioned by Palmik

Thu, 24 Aug 2023 16:17:19 GMT

The best model, Unnatural Code Llama, is not released. Likely because it's trained on GPT4 based data, and might violate OpenAI TOS, because as per the "Unnatural" paper [1], the "unnatural" data is generated with the help of some LLM -- and you would want to use as good of an LLM as possible. [1] https://arxiv.org/pdf/2212.09689.pdf

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

Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor — HN submission

Wed, 11 Jan 2023 03:06:03 GMT

Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor

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