|
__init__.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
baichuan_model.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
distributed.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
fused_bias_gelu.py
|
change megatron to ascendspeed
|
2023-06-10 21:26:01 +08:00 |
|
fused_layer_norm.py
|
create megatron core
|
2023-07-24 15:00:57 +08:00 |
|
fused_softmax.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
glu_activations.py
|
change megatron to ascendspeed
|
2023-06-10 21:26:01 +08:00 |
|
gpt_model.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
internlm_model.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
language_model.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
llama2_model.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
llama_model.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
lora_modules.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
lora_utils.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
manual_pipe.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
module.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
positional_embeddings.py
|
create megatron core
|
2023-07-24 15:00:57 +08:00 |
|
transformer.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
triangle_attention.py
|
up
|
2023-09-26 14:30:47 +08:00 |
|
utils.py
|
change megatron to ascendspeed
|
2023-06-10 21:26:01 +08:00 |
