Felix Marty 0036084294 support all, test llama		2023-07-13 15:41:57 +00:00
..
custom_modeling	support all, test llama	2023-07-13 15:41:57 +00:00
__init__.py	have a single gptq quantization type	2023-07-12 15:43:20 +00:00
bloom.py	feat: Add the option to force another dtype than f16. (#513)	2023-06-30 20:30:09 +02:00
causal_lm.py	support all, test llama	2023-07-13 15:41:57 +00:00
flash_causal_lm.py	support all, test llama	2023-07-13 15:41:57 +00:00
flash_llama.py	support all, test llama	2023-07-13 15:41:57 +00:00
flash_neox.py	support all, test llama	2023-07-13 15:41:57 +00:00
flash_rw.py	support all, test llama	2023-07-13 15:41:57 +00:00
flash_santacoder.py	support all, test llama	2023-07-13 15:41:57 +00:00
galactica.py	support all, test llama	2023-07-13 15:41:57 +00:00
gpt_neox.py	support all, test llama	2023-07-13 15:41:57 +00:00
model.py	support all, test llama	2023-07-13 15:41:57 +00:00
mpt.py	support all, test llama	2023-07-13 15:41:57 +00:00
opt.py	support all, test llama	2023-07-13 15:41:57 +00:00
rw.py	support all, test llama	2023-07-13 15:41:57 +00:00
santacoder.py	support all, test llama	2023-07-13 15:41:57 +00:00
seq2seq_lm.py	support all, test llama	2023-07-13 15:41:57 +00:00
t5.py	support all, test llama	2023-07-13 15:41:57 +00:00
types.py	feat(server): support vectorized warpers in flash causal lm (#317)	2023-05-26 12:30:27 +02:00