TwitterAAE

The TwitterAAE corpus of Blodgett et al. (2016) for measuring language model performance in tweets as a function of speaker dialect.

  • Task: language modeling
  • What: ?
  • When: ?
  • Who: ?
  • Language: English (AAE-aligned and White-aligned)
  1. BPB

  2. Denoised inference time (s)

  3. # eval

  4. # train

  5. truncated

  6. # prompt tokens

  7. # output tokens

  8. # trials

02505007501000J1-Jumbo v1(178B)J1-Large v1(7.5B)J1-Grande v1(17B)J1-Grande v2beta (17B)Jurassic-2 Jumbo(178B)Jurassic-2Grande (17B)Jurassic-2 Large(7.5B)Anthropic-LMv4-s3 (52B)BLOOM (176B)Cohere xlargev20220609(52.4B)Cohere largev20220720(13.1B)Cohere mediumv20220720(6.1B)Cohere smallv20220720(410M)Cohere xlargev20221108(52.4B)Cohere mediumv20221108(6.1B)CohereCommand beta(6.1B)CohereCommand beta(52.4B)GPT-J (6B)GPT-NeoX (20B)OPT (175B)OPT (66B)TNLG v2 (530B)TNLG v2 (6.7B)davinci (175B)curie (6.7B)babbage (1.3B)ada (350M)text-davinci-003text-davinci-002text-curie-001text-babbage-001text-ada-001RedPajama-INCITE-Base-v1(3B)