vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

lookup : add prompt lookup decoding example (#4484)

Browse source 
* initial commit, going through initializations

* main loop finished, starting to debug

* BUG: generates gibberish/repeating tokens after a while

* kv_cache management

* Added colors to distinguish drafted tokens (--color). Updated README

* lookup : fix token positions in the draft batch

* lookup : use n_draft from CLI params

* lookup : final touches

---------

Co-authored-by: Leon Ericsson <leon.ericsson@icloud.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
LeonEricsson 2023-12-22 17:05:56 +01:00 • committed by GitHub
parent ba66175132
commit 7082d24cec
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 256 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/CMakeLists.txt
View file

@ -33,6 +33,7 @@ else()
add_subdirectory(simple)
add_subdirectory(speculative)
add_subdirectory(lookahead)
add_subdirectory(lookup)
add_subdirectory(train-text-from-scratch)
if (LLAMA_METAL)
add_subdirectory(metal)