Joshua Lochner 6e2d04e429 Fix slow GemmaTokenizer and improve SPM slow -> fast conversion process (#32191) ... * Remove user-defined tokens which can be obtained through merges * Remove debug line * formatting * Refactor spm slow -> fast converter * revert unnecessary refactor * set comprehension * remove test files * Use `vocab_scores` * Always replace spiece underline with space in decode * we no longer need token filtering * Add save fast load slow unit test * Remove tokenizers version check * Remove duplicate code * Make `<start_of_turn>` and `<end_of_turn>` special tokens * Bias merge priority with length if score is the same * Add unit test for merge priority * CI		2024-07-30 23:36:38 +02:00
..
agents	Updated ruff to the latest version (#31926)	2024-07-23 17:07:31 +02:00
benchmark
bettertransformer	Fixed malapropism error (#26660)	2023-10-09 11:04:57 +02:00
deepspeed	[tests] fix deepspeed zero3 config for test_stage3_nvme_offload (#31881)	2024-07-16 16:11:37 +02:00
extended	Skip tests properly (#31308)	2024-06-26 21:59:08 +01:00
fixtures	Implementation of SuperPoint and AutoModelForKeypointDetection (#28966)	2024-03-19 14:43:02 +00:00
fsdp	Llama et al. / FSDP : Fix breaking change in 4.40 for FSDP (#31161)	2024-06-26 14:50:08 +01:00
generation	Generate: end-to-end compilation (#30788)	2024-07-29 10:52:13 +01:00
models	Fix slow GemmaTokenizer and improve SPM slow -> fast conversion process (#32191)	2024-07-30 23:36:38 +02:00
optimization	fix: Fixed the 1st argument name in classmethods (#31907)	2024-07-11 12:11:50 +01:00
peft_integration	FIX [CI]: Fix failing tests for peft integration (#29330)	2024-02-29 03:56:16 +01:00
pipelines	[pipeline] fix padding for 1-d tensors (#31776)	2024-07-29 21:24:42 +08:00
quantization	Support dequantizing GGUF FP16 format (#31783)	2024-07-24 17:59:59 +02:00
repo_utils	Allow # Ignore copy (#27328)	2023-12-07 10:00:08 +01:00
sagemaker	Fixed log messages that are resulting in TypeError due to too many arguments (#32017)	2024-07-17 10:56:44 +01:00
tokenization	Skip tests properly (#31308)	2024-06-26 21:59:08 +01:00
trainer	Enhancing SFT Training Efficiency Using Packing and FlashAttention2 with Position IDs (#31629)	2024-07-23 15:56:41 +02:00
utils	Make static cache compatible with torch.export (#32168)	2024-07-29 18:19:15 +01:00
__init__.py
test_backbone_common.py	Align backbone stage selection with out_indices & out_features (#27606)	2023-12-20 18:33:17 +00:00
test_configuration_common.py	Refactor: Removed un-necessary object base class (#32230)	2024-07-26 10:33:02 +02:00
test_feature_extraction_common.py	Split common test from core tests (#24284)	2023-06-15 07:30:24 -04:00
test_image_processing_common.py	Skip tests properly (#31308)	2024-06-26 21:59:08 +01:00
test_image_transforms.py	fix: center_crop occasionally outputs off-by-one dimension matrix (#30934)	2024-05-21 13:56:52 +01:00
test_modeling_common.py	Flash-Attn: fix generation when no attention mask or no pading (#32241)	2024-07-26 14:45:55 +05:00
test_modeling_flax_common.py	add sdpa to ViT [follow up of #29325] (#30555)	2024-05-16 10:56:11 +01:00
test_modeling_tf_common.py	Port IDEFICS to tensorflow (#26870)	2024-05-13 15:59:46 +01:00
test_pipeline_mixin.py	fix: Fixed raising TypeError instead of ValueError for invalid type (#32111)	2024-07-22 17:46:17 +01:00
test_processing_common.py	add initial design for uniform processors + align model (#31197)	2024-06-13 16:27:16 +02:00
test_sequence_feature_extraction_common.py	Fix typo (#25966)	2023-09-05 10:12:25 +02:00
test_tokenization_common.py	Return assistant generated tokens mask in apply_chat_template (#30650)	2024-07-22 18:24:43 +01:00