github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-06 03:20:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

[misc] update pre-commit and run all files (#4752)

Browse Source 
* [misc] update pre-commit

* [misc] run pre-commit

* [misc] remove useless configuration files

* [misc] ignore cuda for clang-format
This commit is contained in:
Hongxin Liu
2023-09-19 14:20:26 +08:00
committed by GitHub
parent 3c6b831c26
commit 079bf3cb26
1268 changed files with 50037 additions and 38444 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
colossalai/shardformer/modeling/chatglm2_6b/configuration_chatglm.py
View File

@@ -4,32 +4,34 @@ from transformers import PretrainedConfig
class ChatGLMConfig(PretrainedConfig):
model_type = "chatglm"
def __init__(self,
num_layers=28,
padded_vocab_size=65024,
hidden_size=4096,
ffn_hidden_size=13696,
kv_channels=128,
num_attention_heads=32,
seq_length=2048,
hidden_dropout=0.0,
attention_dropout=0.0,
layernorm_epsilon=1e-5,
rmsnorm=True,
apply_residual_connection_post_layernorm=False,
post_layer_norm=True,
add_bias_linear=False,
add_qkv_bias=False,
bias_dropout_fusion=True,
multi_query_attention=False,
multi_query_group_num=1,
apply_query_key_layer_scaling=True,
attention_softmax_in_fp32=True,
fp32_residual_connection=False,
quantization_bit=0,
pre_seq_len=None,
prefix_projection=False,
**kwargs):
def __init__(
self,
num_layers=28,
padded_vocab_size=65024,
hidden_size=4096,
ffn_hidden_size=13696,
kv_channels=128,
num_attention_heads=32,
seq_length=2048,
hidden_dropout=0.0,
attention_dropout=0.0,
layernorm_epsilon=1e-5,
rmsnorm=True,
apply_residual_connection_post_layernorm=False,
post_layer_norm=True,
add_bias_linear=False,
add_qkv_bias=False,
bias_dropout_fusion=True,
multi_query_attention=False,
multi_query_group_num=1,
apply_query_key_layer_scaling=True,
attention_softmax_in_fp32=True,
fp32_residual_connection=False,
quantization_bit=0,
pre_seq_len=None,
prefix_projection=False,
**kwargs,
):
self.num_layers = num_layers
self.vocab_size = padded_vocab_size
self.padded_vocab_size = padded_vocab_size