tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)

* tests : add test-tokenizer-0.sh

* unicode : add all unicode number ranges

* starcoder : fix pre-tokenizer

* tests : add test that fails with DeepSeek tokenizers

* falcon : fix regex

* unicode : regenerate unicode tables

* refact : add tokenizer model

* lint : fix

* tests : disable failing tests

ggml-ci

* refact : add tests files

ggml-ci

* convert : print -> logging

ggml-ci

* lint : fix

* unicode : digit -> number

* phi-3 : update
This commit is contained in:
Georgi Gerganov 2024-05-04 08:32:32 +03:00 committed by GitHub
parent a2ac89d6ef
commit 92139b90af
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
41 changed files with 903 additions and 719 deletions

View file

@ -77,11 +77,10 @@ test: $(TEST_TARGETS)
./$$test_target $(CURDIR)/models/ggml-vocab-llama-bpe.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-phi-3.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-falcon.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-deepseek-coder.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-deepseek-llm.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-bert-bge.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-starcoder.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-gpt-2.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-refact.gguf; \
elif [ "$$test_target" = "tests/test-tokenizer-1-spm" ]; then \
continue; \
elif [ "$$test_target" = "tests/test-tokenizer-1-bpe" ]; then \