root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-28 12:24:35 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
9b38f8bf65
llama.cpp/examples/lookup
History
Francis Couture-Harpin 9b38f8bf65 Merge branch 'master' into compilade/refactor-kv-cache
2024-07-04 17:33:52 -04:00
..
CMakeLists.txt build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
lookup-create.cpp common : refactor cli arg parsing (#7675) 2024-06-04 21:23:39 +03:00
lookup-merge.cpp build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
lookup-stats.cpp common : refactor cli arg parsing (#7675) 2024-06-04 21:23:39 +03:00
lookup.cpp examples : replace llama_kv_cache_seq_* with llama_past_seq_* 2024-06-11 23:27:04 -04:00
README.md Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258) 2024-07-02 12:18:10 -04:00

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