1
0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-25 19:08:44 +01:00
llama.cpp/examples/lookup
Georgi Gerganov afa8a9ec9b
llama : add llama_vocab, functions -> methods, naming ()
* llama : functions -> methods ()

* llama : add struct llama_vocab to the API ()

ggml-ci

* hparams : move vocab params to llama_vocab ()

ggml-ci

* vocab : more pimpl ()

ggml-ci

* vocab : minor tokenization optimizations ()

ggml-ci

Co-authored-by: Diego Devesa <slarengh@gmail.com>

* lora : update API names ()

ggml-ci

* llama : update API names to use correct prefix ()

* llama : update API names to use correct prefix

ggml-ci

* cont

ggml-ci

* cont

ggml-ci

* minor [no ci]

* vocab : llama_vocab_add_[be]os -> llama_vocab_get_add_[be]os ()

ggml-ci

* vocab : llama_vocab_n_vocab -> llama_vocab_n_tokens ()

ggml-ci

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
2025-01-12 11:32:42 +02:00
..
CMakeLists.txt ggml : move AMX to the CPU backend () 2024-11-29 21:54:58 +01:00
lookup-create.cpp llama : refactor src/llama.cpp () 2025-01-03 10:18:53 +02:00
lookup-merge.cpp common : use common_ prefix for common library functions () 2024-10-10 22:57:42 +02:00
lookup-stats.cpp llama : refactor src/llama.cpp () 2025-01-03 10:18:53 +02:00
lookup.cpp llama : add llama_vocab, functions -> methods, naming () 2025-01-12 11:32:42 +02:00
README.md Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. () 2024-07-02 12:18:10 -04:00

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