text-generation-inference/server/text_generation_server/models/custom_modeling
2023-10-23 12:29:25 +02:00
..
__init__.py feat(server): flash santacoder (#153) 2023-04-03 19:06:42 +02:00
bloom_modeling.py feat: format code (#1070) 2023-09-27 12:22:09 +02:00
flash_llama_modeling.py feat: paged attention v2 (#1183) 2023-10-23 12:29:25 +02:00
flash_mistral_modeling.py feat: paged attention v2 (#1183) 2023-10-23 12:29:25 +02:00
flash_neox_modeling.py feat: paged attention v2 (#1183) 2023-10-23 12:29:25 +02:00
flash_rw_modeling.py feat: paged attention v2 (#1183) 2023-10-23 12:29:25 +02:00
flash_santacoder_modeling.py feat: paged attention v2 (#1183) 2023-10-23 12:29:25 +02:00
idefics_config.py small fix on idefics (#954) 2023-09-01 18:44:34 +02:00
idefics_image_processing.py Hotfixing idefics base64 parsing. (#1103) 2023-10-05 13:35:26 +02:00
idefics_modeling.py feat: format code (#1070) 2023-09-27 12:22:09 +02:00
idefics_perceiver.py feat: format code (#1070) 2023-09-27 12:22:09 +02:00
idefics_processing.py Hotfixing idefics base64 parsing. (#1103) 2023-10-05 13:35:26 +02:00
idefics_vision.py feat: format code (#1070) 2023-09-27 12:22:09 +02:00
mpt_modeling.py chore: fix typo in mpt_modeling.py (#737) 2023-07-31 15:43:44 +02:00
neox_modeling.py Fix: Replace view() with reshape() in neox_modeling.py to resolve RuntimeError (#1155) 2023-10-19 11:54:26 +02:00
opt_modeling.py Complete FastLinear.load parameters in OPTDecoder initialization (#1060) 2023-09-27 12:25:59 +02:00
t5_modeling.py Fixing t5 loading. (#1042) 2023-09-25 12:22:28 +02:00