Delete config.py
Browse files
config.py
DELETED
@@ -1,43 +0,0 @@
|
|
1 |
-
from transformers import PretrainedConfig
|
2 |
-
|
3 |
-
|
4 |
-
class BigBrainConfig(PretrainedConfig):
|
5 |
-
model_type = 'big-brain-lm'
|
6 |
-
|
7 |
-
def __init__(
|
8 |
-
self,
|
9 |
-
vocab_size=50265,
|
10 |
-
hidden_size=768,
|
11 |
-
num_hidden_layers=12,
|
12 |
-
num_attention_heads=12,
|
13 |
-
intermediate_size=3072,
|
14 |
-
hidden_act='gelu',
|
15 |
-
hidden_dropout_probability=0.1,
|
16 |
-
attention_probs_dropout_prob=0.1,
|
17 |
-
max_position_embeddings=512,
|
18 |
-
initializer_range=0.02,
|
19 |
-
layer_norm_eps=1e-6,
|
20 |
-
rope_theta=10000,
|
21 |
-
sos_token_id=0,
|
22 |
-
pad_token_id=1,
|
23 |
-
eos_token_id=2,
|
24 |
-
unk_token_id=3,
|
25 |
-
**kwargs
|
26 |
-
):
|
27 |
-
self.vocab_size = vocab_size
|
28 |
-
self.hidden_size = hidden_size
|
29 |
-
self.num_hidden_layers = num_hidden_layers
|
30 |
-
self.num_attention_heads = num_attention_heads
|
31 |
-
self.intermediate_size = intermediate_size
|
32 |
-
self.hidden_act = hidden_act
|
33 |
-
self.hidden_dropout_probability = hidden_dropout_probability
|
34 |
-
self.attention_probs_dropout_prob = attention_probs_dropout_prob
|
35 |
-
self.max_position_embeddings = max_position_embeddings
|
36 |
-
self.initializer_range = initializer_range
|
37 |
-
self.layer_norm_eps = layer_norm_eps
|
38 |
-
self.rope_theta = rope_theta
|
39 |
-
self.sos_token_id = sos_token_id
|
40 |
-
self.pad_token_id = pad_token_id
|
41 |
-
self.eos_token_id = eos_token_id
|
42 |
-
self.unk_token_id = unk_token_id
|
43 |
-
super().__init__(**kwargs)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|