Evan-Lin commited on
Commit
33b30a2
·
verified ·
1 Parent(s): 05df315

Upload checkpoint artifacts

Browse files
ono_anna-moshiko-lora-r64-s1/checkpoints/checkpoint_001000/consolidated/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dim": 4096,
3
+ "text_card": 32000,
4
+ "existing_text_padding_id": 3,
5
+ "n_q": 16,
6
+ "dep_q": 8,
7
+ "card": 2048,
8
+ "num_heads": 32,
9
+ "num_layers": 32,
10
+ "hidden_scale": 4.125,
11
+ "causal": true,
12
+ "layer_scale": null,
13
+ "context": 3000,
14
+ "max_period": 10000,
15
+ "gating": "silu",
16
+ "norm": "rms_norm_f32",
17
+ "positional_embedding": "rope",
18
+ "depformer_dim": 1024,
19
+ "depformer_dim_feedforward": 4224,
20
+ "depformer_num_heads": 16,
21
+ "depformer_num_layers": 6,
22
+ "depformer_layer_scale": null,
23
+ "depformer_multi_linear": true,
24
+ "depformer_context": 8,
25
+ "depformer_max_period": 10000,
26
+ "depformer_gating": "silu",
27
+ "depformer_pos_emb": "none",
28
+ "depformer_weights_per_step": true,
29
+ "delays": [
30
+ 0,
31
+ 0,
32
+ 1,
33
+ 1,
34
+ 1,
35
+ 1,
36
+ 1,
37
+ 1,
38
+ 1,
39
+ 0,
40
+ 1,
41
+ 1,
42
+ 1,
43
+ 1,
44
+ 1,
45
+ 1,
46
+ 1
47
+ ],
48
+ "lora": true,
49
+ "lora_rank": 64,
50
+ "lora_scaling": 1.0
51
+ }