.. |
custom_modeling
|
feat: add quant to mixtral (#1337)
|
2023-12-12 17:55:03 +01:00 |
__init__.py
|
chore: formatting
|
2023-12-11 14:49:52 +01:00 |
bloom.py
|
fix: fix gpt-q params loading
|
2023-12-14 11:02:16 +01:00 |
cache_manager.py
|
feat: add mistral model (#1071)
|
2023-09-28 09:55:47 +02:00 |
causal_lm.py
|
chore: formatting
|
2023-12-11 14:49:52 +01:00 |
flash_causal_lm.py
|
chore: formatting
|
2023-12-11 14:49:52 +01:00 |
flash_llama.py
|
fix: fix gpt-q params loading
|
2023-12-14 11:02:16 +01:00 |
flash_mistral.py
|
fix: fix gpt-q params loading
|
2023-12-14 11:02:16 +01:00 |
flash_mixtral.py
|
chore: formatting
|
2023-12-11 14:49:52 +01:00 |
flash_neox.py
|
fix: fix gpt-q params loading
|
2023-12-14 11:02:16 +01:00 |
flash_rw.py
|
fix: fix gpt-q params loading
|
2023-12-14 11:02:16 +01:00 |
flash_santacoder.py
|
fix: fix gpt-q params loading
|
2023-12-14 11:02:16 +01:00 |
galactica.py
|
fix: fix gpt-q params loading
|
2023-12-14 11:02:16 +01:00 |
gpt_neox.py
|
fix: fix gpt-q params loading
|
2023-12-14 11:02:16 +01:00 |
idefics.py
|
enable bfloat16 for cpu (#1034)
|
2023-09-19 17:19:28 +02:00 |
idefics_causal_lm.py
|
chore: formatting
|
2023-12-11 14:49:52 +01:00 |
model.py
|
chore: formatting
|
2023-12-11 14:49:52 +01:00 |
mpt.py
|
fix: fix gpt-q params loading
|
2023-12-14 11:02:16 +01:00 |
opt.py
|
fix: fix gpt-q params loading
|
2023-12-14 11:02:16 +01:00 |
rw.py
|
enable bfloat16 for cpu (#1034)
|
2023-09-19 17:19:28 +02:00 |
santacoder.py
|
enable bfloat16 for cpu (#1034)
|
2023-09-19 17:19:28 +02:00 |
seq2seq_lm.py
|
chore: formatting
|
2023-12-11 14:49:52 +01:00 |
t5.py
|
enable bfloat16 for cpu (#1034)
|
2023-09-19 17:19:28 +02:00 |
types.py
|
chore: formatting
|
2023-12-11 14:49:52 +01:00 |