Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 06:10:29 +01:00
Code Issues Packages Projects Releases Wiki Activity
1b67731e18
llama.cpp/examples/lookup
History
Jared Van Bortel 1b67731e18
BERT tokenizer fixes (#6498) 
Key changes:
* BERT conversion: fix abuse of LlamaHfVocab, do not set BOS or EOS
* Nomic Embed conversion: pad vocab instead of slicing embedding tensor
* llama_tokenize: handle added special tokens like HF does
2024-04-09 13:44:08 -04:00
..
CMakeLists.txt lookup: complement data from context with general text statistics (#5479) 2024-03-23 01:24:36 +01:00
lookup-create.cpp BERT tokenizer fixes (#6498) 2024-04-09 13:44:08 -04:00
lookup-merge.cpp lookup: complement data from context with general text statistics (#5479) 2024-03-23 01:24:36 +01:00
lookup-stats.cpp BERT tokenizer fixes (#6498) 2024-04-09 13:44:08 -04:00
lookup.cpp BERT tokenizer fixes (#6498) 2024-04-09 13:44:08 -04:00
README.md lookup : add prompt lookup decoding example (#4484) 2023-12-22 18:05:56 +02:00

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