| .. |
|
custom_modeling
|
feat(server): support RefinedWeb models (#379)
|
2023-05-30 18:25:19 +02:00 |
|
__init__.py
|
feat(server): support RefinedWeb models (#379)
|
2023-05-30 18:25:19 +02:00 |
|
bloom.py
|
fix(server): fix quantization
|
2023-05-30 13:56:03 +02:00 |
|
causal_lm.py
|
feat(server): support vectorized warpers in flash causal lm (#317)
|
2023-05-26 12:30:27 +02:00 |
|
flash_causal_lm.py
|
feat(server): support vectorized warpers in flash causal lm (#317)
|
2023-05-26 12:30:27 +02:00 |
|
flash_llama.py
|
feat(server): support trust_remote_code (#363)
|
2023-05-23 20:40:39 +02:00 |
|
flash_neox.py
|
feat(server): support trust_remote_code (#363)
|
2023-05-23 20:40:39 +02:00 |
|
flash_rw.py
|
feat(server): support RefinedWeb models (#379)
|
2023-05-30 18:25:19 +02:00 |
|
flash_santacoder.py
|
feat(server): support trust_remote_code (#363)
|
2023-05-23 20:40:39 +02:00 |
|
galactica.py
|
fix(server): fix quantization
|
2023-05-30 13:56:03 +02:00 |
|
gpt_neox.py
|
fix(server): fix quantization
|
2023-05-30 13:56:03 +02:00 |
|
model.py
|
fix(server): fix decode token (#334)
|
2023-05-16 23:23:27 +02:00 |
|
opt.py
|
feat(server): support trust_remote_code (#363)
|
2023-05-23 20:40:39 +02:00 |
|
rw.py
|
feat(server): support RefinedWeb models (#379)
|
2023-05-30 18:25:19 +02:00 |
|
santacoder.py
|
feat(server): support trust_remote_code (#363)
|
2023-05-23 20:40:39 +02:00 |
|
seq2seq_lm.py
|
feat(server): support vectorized warpers in flash causal lm (#317)
|
2023-05-26 12:30:27 +02:00 |
|
t5.py
|
fix(server): fix quantization
|
2023-05-30 13:56:03 +02:00 |
|
types.py
|
feat(server): support vectorized warpers in flash causal lm (#317)
|
2023-05-26 12:30:27 +02:00 |
b8b950b37c