745aa5319b
* llama : deprecate llama_kv_self_ API ggml-ci * llama : allow llama_memory_(nullptr) ggml-ci * memory : add flag for optional data clear in llama_memory_clear ggml-ci |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| lookup-create.cpp | ||
| lookup-merge.cpp | ||
| lookup-stats.cpp | ||
| lookup.cpp | ||
| 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/ggml-org/llama.cpp/pull/4484 https://github.com/ggml-org/llama.cpp/issues/4226