jaime-m-p 37bef89433 tokenizer : BPE fixes (#7530) ... * Random test: add_bos_token, add_eos_token * Random test: add BPE models for testing * Custom regex split fails with codepoint 0 * Fix falcon punctuation regex * Refactor llm_tokenizer_bpe: move code to constructor * Move 'add_special_bos/eos' logic to llm_tokenizer_bpe * Move tokenizer flags to vocab structure. * Default values for special_add_bos/eos * Build vocab.special_tokens_cache using vocab token types * Generalize 'jina-v2' per token attributes * Fix unicode whitespaces (deepseek-coder, deepseek-llm) * Skip missing byte tokens (falcon) * Better unicode data generation * Replace char32_t with uint32_t		2024-06-18 18:40:52 +02:00
..
LlamaConfig.cmake.in	ggml : remove OpenCL (#7735)	2024-06-04 21:23:20 +03:00
build-info.cmake	…
build-info.sh	…
check-requirements.sh	Move convert.py to examples/convert-legacy-llama.py (#7430)	2024-05-30 21:40:00 +10:00
ci-run.sh	…
compare-commits.sh	llama-bench : allow using a different printer for stderr with -oe (#7722)	2024-06-04 14:32:42 +02:00
compare-llama-bench.py	ggml : remove OpenCL (#7735)	2024-06-04 21:23:20 +03:00
convert-gg.sh	Move convert.py to examples/convert-legacy-llama.py (#7430)	2024-05-30 21:40:00 +10:00
debug-test.sh	…
gen-authors.sh	…
gen-build-info-cpp.cmake	…
gen-unicode-data.py	tokenizer : BPE fixes (#7530)	2024-06-18 18:40:52 +02:00
get-flags.mk	…
get-hellaswag.sh	`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	2024-06-13 00:41:52 +01:00
get-pg.sh	…
get-wikitext-2.sh	`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	2024-06-13 00:41:52 +01:00
get-wikitext-103.sh	`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	2024-06-13 00:41:52 +01:00
get-winogrande.sh	`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	2024-06-13 00:41:52 +01:00
hf.sh	`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	2024-06-13 00:41:52 +01:00
install-oneapi.bat	…
pod-llama.sh	`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	2024-06-13 00:41:52 +01:00
qnt-all.sh	`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	2024-06-13 00:41:52 +01:00
run-all-perf.sh	…
run-all-ppl.sh	`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	2024-06-13 00:41:52 +01:00
run-with-preset.py	`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	2024-06-13 00:41:52 +01:00
server-llm.sh	`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	2024-06-13 00:41:52 +01:00
sync-ggml-am.sh	ggml : remove OpenCL (#7735)	2024-06-04 21:23:20 +03:00
sync-ggml.last	ggml : sync	2024-06-18 09:50:45 +03:00
sync-ggml.sh	ggml : remove OpenCL (#7735)	2024-06-04 21:23:20 +03:00
verify-checksum-models.py	…
xxd.cmake	…