|
custom_modeling
|
fix tp
|
2023-04-06 17:27:32 +02:00 |
|
__init__.py
|
feat(server): add flash attention llama
|
2023-04-06 13:45:08 +02:00 |
|
bloom.py
|
feat(clients): Python client (#103)
|
2023-03-07 18:52:22 +01:00 |
|
causal_lm.py
|
better decode
|
2023-04-06 13:45:08 +02:00 |
|
flash_causal_lm.py
|
use all tokens
|
2023-04-06 13:45:08 +02:00 |
|
flash_llama.py
|
fix tp
|
2023-04-06 17:27:32 +02:00 |
|
flash_neox.py
|
fix tp
|
2023-04-06 17:27:32 +02:00 |
|
flash_santacoder.py
|
fix llama tokenizer
|
2023-04-06 17:07:58 +02:00 |
|
galactica.py
|
better decode
|
2023-04-06 13:45:08 +02:00 |
|
gpt_neox.py
|
fix(server): add position ids to neox (#126)
|
2023-03-15 13:12:49 +01:00 |
|
model.py
|
update transformers
|
2023-04-06 13:45:08 +02:00 |
|
santacoder.py
|
feat(clients): Python client (#103)
|
2023-03-07 18:52:22 +01:00 |
|
seq2seq_lm.py
|
better decode
|
2023-04-06 13:45:08 +02:00 |
|
t5.py
|
feat(clients): Python client (#103)
|
2023-03-07 18:52:22 +01:00 |
|
types.py
|
feat(clients): Python client (#103)
|
2023-03-07 18:52:22 +01:00 |
