DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM to Date

Re:DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM... by masterofsome on Tuesday December 12, 2023 @11:04AM (#38614009)

You have to look at the pre-trained models and not the "tuned" models. Its number one in that category (which is what I think they are referring to, given the benchmarks are against Mistral and llama)

[ Parent | on HN ]

Re:DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM... by ilc on Tuesday December 12, 2023 @11:11AM (#38614116)

Doesn't the article say this is a LoRA off ORCA? Isn't that a finetune?

[ Parent | on HN ]

Re:DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM... by GaggiX on Tuesday December 12, 2023 @11:19AM (#38614223)

DeciLM-7B-instruct is the finetuned model, not DeciLM-7B.

[ Parent | on HN ]

Re:DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM... by audessuscest on Tuesday December 12, 2023 @11:10AM (#38614088)

thanks for the clarification

[ Parent | on HN ]