Página Principal Explorar Ajuda
Iniciar Sessão
cturan
/
llama.cpp
mirror de https://github.com/cturan/llama.cpp
1
0
Fork 0
Ficheiros Problemas 0 Wiki
Árvore: ff252ea48e
Ramos Etiquetas
llama.cpp
/
examples
/
lookup
Xuan Son Nguyen cda0e4b648 llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745) há 1 ano atrás
..
CMakeLists.txt 1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) há 1 ano atrás
README.md 07a3fc0608 Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258) há 1 ano atrás
lookup-create.cpp 7eee341bee common : use common_ prefix for common library functions (#9805) há 1 ano atrás
lookup-merge.cpp 7eee341bee common : use common_ prefix for common library functions (#9805) há 1 ano atrás
lookup-stats.cpp 7eee341bee common : use common_ prefix for common library functions (#9805) há 1 ano atrás
lookup.cpp cda0e4b648 llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745) há 1 ano atrás

README.md

llama.cpp/examples/lookup

Demonstration of Prompt Lookup Decoding

https://github.com/apoorvumang/prompt-lookup-decoding

The key parameters for lookup decoding are ngram_min, ngram_max and n_draft. The first two determine the size of the ngrams to search for in the prompt for a match. The latter specifies how many subsequent tokens to draft if a match is found.

More info:

https://github.com/ggerganov/llama.cpp/pull/4484 https://github.com/ggerganov/llama.cpp/issues/4226