FlyingPotatoZ

How should I verify that the model supports the functionality of 200K context length ?

1

因为Yi-6B-200K 和Yi-34B-200K两个模型看上去都拥有了200K长度的context能力，这相当令人振奋（GPT4-turbo 仅仅只有128K的能力）。 这一点吸引了海内外很多业内人士的关注，我对此很好奇，想知道我应该如果验证这一点，目前官方好像没有提供相关实验数据或者guide，有没有人能给予一点帮助，谢谢。 ----------------------------------------------------------------------- Because both models Yi-6B-200K and Yi-34B-200K seem to have 200K length context capabilities, this is quite exciting (GPT4-turbo only has 128K capabilities). This has attracted...

Hello guys: Because there is no dependence on computation and communication, I think multi-stream pipeline parallelism can hide communication time to improve performance. I didn't find how to configure the...

Use the gpt2 model, and test the quantification accuracy. model download: https://github.com/quic/aimet-model-zoo/releases/download/torch_gpt2/gpt2_wikitext_finetune.tar.gz test data：wikitext-2-raw-v1, Item | Description -- | -- AIMET | 1.28.0 Linux kernel | 20.04 cuda | 11.6...