koboldcpp/tests
Tristan Druyen 007489e895
Fix phi3 chat template confusion with zephyr (#7449)
* Fix phi3 template matching vs zephyr

* Add regression test for new phi3 chat template

* Implement review suggestions

* Fix phi3 jinja test templates & match by <|end|>

* Apply suggestion

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* Add all phi3 template variants in tests

* Remove unneeded message trimming

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* Fix tests to not expect trimmed messages

---------

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
2024-05-23 16:15:15 +02:00
..
.gitignore
CMakeLists.txt llama : lookup word in vocab before doing BPE merges (#7193) 2024-05-11 11:12:06 +03:00
get-model.cpp
get-model.h
run-json-schema-to-grammar.mjs
test-autorelease.cpp ggml : add numa options (#5377) 2024-02-16 11:31:07 +02:00
test-backend-ops.cpp cuda : fix rope + add tests (#7452) 2024-05-22 11:01:35 +03:00
test-c.c
test-chat-template.cpp Fix phi3 chat template confusion with zephyr (#7449) 2024-05-23 16:15:15 +02:00
test-double-float.cpp
test-grad0.cpp ggml : remove ggml_flash_attn and ggml_flash_ff (#7463) 2024-05-23 10:00:44 +03:00
test-grammar-integration.cpp Add left recursion check: quit early instead of going into an infinite loop (#7083) 2024-05-14 15:25:56 +10:00
test-grammar-parser.cpp
test-json-schema-to-grammar.cpp JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143) 2024-05-08 21:53:08 +02:00
test-llama-grammar.cpp ggml, common, examples, tests : fixed type arguments in printf (#5528) 2024-02-18 18:20:12 +02:00
test-model-load-cancel.cpp
test-opt.cpp
test-quantize-fns.cpp
test-quantize-perf.cpp ggml : add mmla kernels for quantized GEMM (#4966) 2024-02-11 15:22:33 +02:00
test-rope.cpp
test-sampling.cpp
test-tokenizer-0.cpp tests : add test-tokenizer-0.sh + fix some tokenizers (#7036) 2024-05-04 08:32:32 +03:00
test-tokenizer-0.py py : logging and flake8 suppression refactoring (#7081) 2024-05-05 08:07:48 +03:00
test-tokenizer-0.sh tests : test-tokenizer-0.sh print more info (#7402) 2024-05-21 19:53:48 +03:00
test-tokenizer-1-bpe.cpp llama : lookup word in vocab before doing BPE merges (#7193) 2024-05-11 11:12:06 +03:00
test-tokenizer-1-spm.cpp
test-tokenizer-random.py Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425) 2024-05-21 14:39:48 +02:00