shaltielshmid 3961e32390 [WIP] Add support for Mistral-Nemo by supporting head_dim through config (#2254) ... * Support passing head_dim through config * Using `head_dim` as a fallback is necessary since it's a non standard key in mistralConfig (as defined in transformers). * Shorter diff. --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>		2024-07-23 15:00:07 +02:00
..
custom_modeling	[WIP] Add support for Mistral-Nemo by supporting head_dim through config (#2254)	2024-07-23 15:00:07 +02:00
__init__.py	Fixing mistral nemo. (#2276)	2024-07-23 11:16:03 +02:00
bloom.py	Refactor dead code - Removing all flash_xxx.py files. (#2166)	2024-07-05 10:29:56 +02:00
causal_lm.py	Hotfix: fix MPT after recent refactor (#2257)	2024-07-19 14:42:35 +02:00
flash_causal_lm.py	Fixing mistral nemo. (#2276)	2024-07-23 11:16:03 +02:00
flash_mistral.py	Refactor dead code - Removing all flash_xxx.py files. (#2166)	2024-07-05 10:29:56 +02:00
galactica.py	Refactor dead code - Removing all flash_xxx.py files. (#2166)	2024-07-05 10:29:56 +02:00
globals.py	feat(fp8): use fbgemm kernels and load fp8 weights directly (#2248)	2024-07-20 19:02:04 +02:00
idefics_causal_lm.py	Enable multiple LoRa adapters (#2010)	2024-06-25 14:46:27 -04:00
idefics.py	Move quantized weight handling out of the Weights class (#2194)	2024-07-09 20:04:03 +02:00
mamba.py	Move quantized weight handling out of the Weights class (#2194)	2024-07-09 20:04:03 +02:00
model.py	feat(fp8): use fbgemm kernels and load fp8 weights directly (#2248)	2024-07-20 19:02:04 +02:00
pali_gemma.py	Refactor dead code - Removing all flash_xxx.py files. (#2166)	2024-07-05 10:29:56 +02:00
seq2seq_lm.py	Move quantized weight handling out of the Weights class (#2194)	2024-07-09 20:04:03 +02:00
types.py	chore: add pre-commit (#1569)	2024-02-16 11:58:58 +01:00
vlm_causal_lm.py	feat(fp8): use fbgemm kernels and load fp8 weights directly (#2248)	2024-07-20 19:02:04 +02:00