File: README.md

package info (click to toggle)
llama.cpp 8064%2Bdfsg-1
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 76,488 kB
  • sloc: cpp: 353,828; ansic: 51,268; python: 30,090; lisp: 11,788; sh: 6,290; objc: 1,395; javascript: 924; xml: 384; makefile: 233
file content (12 lines) | stat: -rw-r--r-- 485 bytes parent folder | download 
1
2
3
4
5
6
7
8
9
10
11
12
 
# 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/ggml-org/llama.cpp/pull/4484
https://github.com/ggml-org/llama.cpp/issues/4226