Hoglet-33 commited on
Commit
d718e7b
·
verified ·
1 Parent(s): fdea4cb

Create configuration_pebble.py

Browse files
Files changed (1) hide show
  1. configuration_pebble.py +40 -0
configuration_pebble.py ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from transformers import PretrainedConfig
2
+
3
+ class PebbleConfig(PretrainedConfig):
4
+ model_type = "pebble_25m"
5
+
6
+ def __init__(
7
+ self,
8
+ vocab_size=2048,
9
+ d_model=608,
10
+ n_blocks=8,
11
+ n_heads=8,
12
+ att_hidden=2432,
13
+ rope_theta=10000.0,
14
+ seq_len=2048,
15
+ mamba_d_state=128,
16
+ mamba_d_conv=4,
17
+ mamba_expand=2,
18
+ mamba_headdim=64,
19
+ block_pattern="3:1 mamba:attn",
20
+ bos_token_id=1,
21
+ eos_token_id=1,
22
+ **kwargs,
23
+ ):
24
+ self.vocab_size = vocab_size
25
+ self.d_model = d_model
26
+ self.n_blocks = n_blocks
27
+ self.n_heads = n_heads
28
+ self.att_hidden = att_hidden
29
+ self.rope_theta = rope_theta
30
+ self.seq_len = seq_len
31
+ self.mamba_d_state = mamba_d_state
32
+ self.mamba_d_conv = mamba_d_conv
33
+ self.mamba_expand = mamba_expand
34
+ self.mamba_headdim = mamba_headdim
35
+ self.block_pattern = block_pattern
36
+ super().__init__(
37
+ bos_token_id=bos_token_id,
38
+ eos_token_id=eos_token_id,
39
+ **kwargs,
40
+ )