Nicolas Patry 49b4b33e80 feat(server): Update convert logic. (#483) ... Should be more robust to shared tensors (ok when using `from_pretrained). But forcing us to add new checks in our loading code (since the chosen key to keep might be different from `transformers`). --------- Co-authored-by: Ubuntu <ubuntu@ip-172-31-41-161.ec2.internal>		2023-06-23 12:40:46 +02:00
..
custom_modeling	fix(server): Fixing T5 in case the names are mixed up. (#475)	2023-06-20 18:03:36 +02:00
__init__.py	fix(server): fix warpers on CPU (#472)	2023-06-20 11:06:10 +02:00
bloom.py	feat(server): Rework model loading (#344)	2023-06-08 14:51:52 +02:00
causal_lm.py	feat(server): only compute prefill logprobs when asked (#406)	2023-06-02 17:12:30 +02:00
flash_causal_lm.py	feat(server): pre-allocate past key values for flash causal LM (#412)	2023-06-12 18:30:29 +02:00
flash_llama.py	feat(server): Rework model loading (#344)	2023-06-08 14:51:52 +02:00
flash_neox.py	feat(server): Rework model loading (#344)	2023-06-08 14:51:52 +02:00
flash_rw.py	feat(server): Rework model loading (#344)	2023-06-08 14:51:52 +02:00
flash_santacoder.py	feat(server): Update convert logic. (#483)	2023-06-23 12:40:46 +02:00
galactica.py	feat(server): Rework model loading (#344)	2023-06-08 14:51:52 +02:00
gpt_neox.py	feat(server): Rework model loading (#344)	2023-06-08 14:51:52 +02:00
model.py	fix(server): fix has_position_ids (#395)	2023-06-01 11:41:35 +02:00
opt.py	feat(server): Rework model loading (#344)	2023-06-08 14:51:52 +02:00
rw.py	feat(server): add retry on download (#384)	2023-05-31 10:57:53 +02:00
santacoder.py	feat(server): support trust_remote_code (#363)	2023-05-23 20:40:39 +02:00
seq2seq_lm.py	feat(server): only compute prefill logprobs when asked (#406)	2023-06-02 17:12:30 +02:00
t5.py	feat(server): Rework model loading (#344)	2023-06-08 14:51:52 +02:00
types.py	feat(server): support vectorized warpers in flash causal lm (#317)	2023-05-26 12:30:27 +02:00