- 19 May, 2023 1 commit
-
-
lintangsutawika authored
-
- 10 May, 2023 1 commit
-
-
lintangsutawika authored
-
- 08 May, 2023 1 commit
-
-
haileyschoelkopf authored
-
- 02 May, 2023 2 commits
-
-
haileyschoelkopf authored
-
haileyschoelkopf authored
-
- 24 Apr, 2023 1 commit
-
-
haileyschoelkopf authored
-
- 19 Apr, 2023 1 commit
-
-
haileyschoelkopf authored
-
- 03 May, 2022 1 commit
-
-
Fabrizio Milo authored
-
- 29 Apr, 2022 1 commit
-
- 27 Apr, 2022 1 commit
-
-
jon-tow authored
-
- 26 Apr, 2022 1 commit
-
-
jon-tow authored
-
- 18 Mar, 2022 1 commit
-
-
Jonathan Tow authored
-
- 29 Dec, 2021 1 commit
-
-
thomasw21 authored
-
- 25 Dec, 2021 1 commit
-
-
Igor Ostrovsky authored
bits_per_byte was calculated as average per-byte loglikelihood, which would work if loglikelihood was base-2 log, but it is natural log. To correct for that, bits_per_byte should be divided by math.log(2). Also, it should be true that 2^bits_per_byte == byte_perplexity, which is true after the fix.
-
- 24 Nov, 2021 1 commit
-
-
Jason Phang authored
-
- 11 May, 2021 3 commits
- 10 May, 2021 4 commits
- 05 May, 2021 1 commit
-
-
Leo Gao authored
-
- 03 May, 2021 2 commits
- 02 May, 2021 2 commits
- 29 Mar, 2021 1 commit
-
-
& authored
-
- 27 Mar, 2021 1 commit
-
-
Jonathan Tow authored
-
- 14 Feb, 2021 1 commit
-
-
& authored
-
- 12 Feb, 2021 3 commits