llama.cpp/examples/server/public_legacy
Georgi Gerganov 644fd71b44
sampling : refactor + optimize penalties sampler (#10803)
* sampling : refactor + optimize penalties sampler

ggml-ci

* common : apply ignore_eos as logit bias

ggml-ci

* batched : remove penalties sampler

* params : allow penalty_last_n == -1 to be equal to context size

ggml-ci

* common : by default, move the penalties at the end of the sampling chain

ggml-ci

* common : ignore all EOG tokens

Co-authored-by: Diego Devesa <slarengh@gmail.com>

* common : move back the penalties at the front of the sampling chain

ggml-ci

* readme : restore hint about --ignore-eos flag [no ci]

* llama : minor

ggml-ci

* webui : update

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
2024-12-16 12:31:14 +02:00
..
colorthemes.css
completion.js
favicon.ico
index-new.html sampling : refactor + optimize penalties sampler (#10803) 2024-12-16 12:31:14 +02:00
index.html sampling : refactor + optimize penalties sampler (#10803) 2024-12-16 12:31:14 +02:00
index.js
json-schema-to-grammar.mjs
loading.html
prompt-formats.js
style.css
system-prompts.js
theme-beeninorder.css
theme-ketivah.css
theme-mangotango.css
theme-playground.css
theme-polarnight.css
theme-snowstorm.css