tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-31 22:53:52 -04:00
Code Issues Packages Projects Releases Wiki Activity
Files
b1093
llama.cpp/examples
History
Kawrakow 463173a6c0 llama : speedup tokenization (#2831) 
* Speedup tokenization

On current master it takes ~3.2 seconds to tokenize
Wikitext. With this change it becomes ~525 ms.

* Fixit: it was missing the piece after the last found occurence

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-08-27 16:50:33 +03:00
..
baby-llama
…
beam_search
llama : more tokenizer fixes (#2810)
2023-08-27 14:19:19 +03:00
benchmark
…
convert-llama2c-to-ggml
minor : fix trailing whitespace
2023-08-23 22:37:39 +03:00
embd-input
llama : more tokenizer fixes (#2810)
2023-08-27 14:19:19 +03:00
embedding
llama : more tokenizer fixes (#2810)
2023-08-27 14:19:19 +03:00
gguf
gguf : add 64-bit support (GGUF v2) (#2821)
2023-08-27 14:19:54 +03:00
gptneox-wip
gguf : new file format with flexible meta data (beta) (#2398)
2023-08-21 23:07:43 +03:00
jeopardy
chmod : make scripts executable (#2675)
2023-08-23 17:29:09 +03:00
llama-bench
llama-bench : add model sizes (#2771)
2023-08-25 15:16:19 +02:00
main
llama : more tokenizer fixes (#2810)
2023-08-27 14:19:19 +03:00
metal
gguf : new file format with flexible meta data (beta) (#2398)
2023-08-21 23:07:43 +03:00
perplexity
llama : speedup tokenization (#2831)
2023-08-27 16:50:33 +03:00
quantize
Fix values shown in the quantize tool help (#2735)
2023-08-23 12:57:12 +03:00
quantize-stats
gguf : new file format with flexible meta data (beta) (#2398)
2023-08-21 23:07:43 +03:00
save-load-state
llama : more tokenizer fixes (#2810)
2023-08-27 14:19:19 +03:00
server
llama : more tokenizer fixes (#2810)
2023-08-27 14:19:19 +03:00
simple
llama : more tokenizer fixes (#2810)
2023-08-27 14:19:19 +03:00
train-text-from-scratch
llama : more tokenizer fixes (#2810)
2023-08-27 14:19:19 +03:00
alpaca.sh
…
chat-13B.bat
…
chat-13B.sh
…
chat-persistent.sh
…
chat-vicuna.sh
…
chat.sh
…
CMakeLists.txt
llama : add llama_beam_search() (#2267)
2023-08-25 18:18:48 +03:00
gpt4all.sh
…
json-schema-to-grammar.py
chmod : make scripts executable (#2675)
2023-08-23 17:29:09 +03:00
llama2-13b.sh
…
llama2.sh
…
llama.vim
…
llm.vim
llm.vim : multiline autocompletion, get rid of "^@" (#2543)
2023-08-08 15:07:02 +03:00
make-ggml.py
chmod : make scripts executable (#2675)
2023-08-23 17:29:09 +03:00
Miku.sh
…
reason-act.sh
chmod : make scripts executable (#2675)
2023-08-23 17:29:09 +03:00
server-llama2-13B.sh
chmod : make scripts executable (#2675)
2023-08-23 17:29:09 +03:00