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

13
examples/lookup/README.md Normal file
View file

@ -0,0 +1,13 @@
# 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