mrq/torchscale
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update config file

Browse Source
This commit is contained in:
shumingma 2022-11-26 08:15:08 -08:00
parent 994e4665a2
commit 1354614d44
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
torchscale/architecture/config.py
View File

@ -22,7 +22,7 @@ class EncoderConfig(object):
self.moe_eval_capacity_token_fraction = kwargs.pop("moe_eval_capacity_token_fraction", 0.25)
self.moe_second_expert_policy = kwargs.pop("moe_second_expert_policy", "random")
self.moe_normalize_gate_prob_before_dropping = kwargs.pop("moe_normalize_gate_prob_before_dropping", False)
self.use_xmoe = kwargs.pop("use_xmoe", True)
self.use_xmoe = kwargs.pop("use_xmoe", False)
self.rel_pos_buckets = kwargs.pop("rel_pos_buckets", 0)
self.max_rel_pos = kwargs.pop("max_rel_pos", 0)
self.deepnorm = kwargs.pop("deepnorm", False)
@ -81,7 +81,7 @@ class DecoderConfig(object):
self.moe_eval_capacity_token_fraction = kwargs.pop("moe_eval_capacity_token_fraction", 0.25)
self.moe_second_expert_policy = kwargs.pop("moe_second_expert_policy", "random")
self.moe_normalize_gate_prob_before_dropping = kwargs.pop("moe_normalize_gate_prob_before_dropping", False)
self.use_xmoe = kwargs.pop("use_xmoe", True)
self.use_xmoe = kwargs.pop("use_xmoe", False)
self.rel_pos_buckets = kwargs.pop("rel_pos_buckets", 0)
self.max_rel_pos = kwargs.pop("max_rel_pos", 0)
self.deepnorm = kwargs.pop("deepnorm", False)
@ -141,7 +141,7 @@ class EncoderDecoderConfig(object):
self.moe_eval_capacity_token_fraction = kwargs.pop("moe_eval_capacity_token_fraction", 0.25)
self.moe_second_expert_policy = kwargs.pop("moe_second_expert_policy", "random")
self.moe_normalize_gate_prob_before_dropping = kwargs.pop("moe_normalize_gate_prob_before_dropping", False)
self.use_xmoe = kwargs.pop("use_xmoe", True)
self.use_xmoe = kwargs.pop("use_xmoe", False)
self.rel_pos_buckets = kwargs.pop("rel_pos_buckets", 0)
self.max_rel_pos = kwargs.pop("max_rel_pos", 0)
self.deepnorm = kwargs.pop("deepnorm", False)