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

examples : read chat prompts from a template file (#1196)

2023-05-03 20:58:11 +03:00

chat-persistent.sh

chat-persistent.sh : use bracket expressions in grep (#1564)

2023-05-24 09:16:22 +03:00

chat-vicuna.sh

examples : add chat-vicuna.sh (#1854)

2023-06-15 21:05:53 +03:00

chat.sh

If n_predict == -1, generate forever

2023-03-25 21:51:41 +02:00

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

gitignore : changes for Poetry users + chat examples (#2284)

2023-07-21 13:53:27 +03:00

llama.vim

vim : streaming and more (#2495)

2023-08-08 14:44:48 +03:00

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

MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287)

2023-07-21 11:13:18 +03:00

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