ryan-0608 commited on
Commit
22ec29f
·
verified ·
1 Parent(s): 79ea0be

inputs/d0-shared-random-experts-8b-x4/config.json

Browse files
inputs/d0-shared-random-experts-8b-x4/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DFlashDraftModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoModel": "dflash.DFlashDraftModel"
9
+ },
10
+ "block_size": 16,
11
+ "bos_token_id": 151643,
12
+ "dflash_config": {
13
+ "mask_token_id": 151669,
14
+ "target_layer_ids": [
15
+ 1,
16
+ 9,
17
+ 17,
18
+ 25,
19
+ 33
20
+ ]
21
+ },
22
+ "dtype": "bfloat16",
23
+ "eos_token_id": 151645,
24
+ "head_dim": 128,
25
+ "hidden_act": "silu",
26
+ "hidden_size": 4096,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 12288,
29
+ "layer_types": [
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention"
35
+ ],
36
+ "max_position_embeddings": 40960,
37
+ "max_window_layers": 5,
38
+ "model_type": "qwen3",
39
+ "num_attention_heads": 32,
40
+ "num_hidden_layers": 5,
41
+ "num_key_value_heads": 8,
42
+ "num_target_layers": 36,
43
+ "rms_norm_eps": 1e-06,
44
+ "rope_scaling": null,
45
+ "rope_theta": 1000000,
46
+ "sliding_window": null,
47
+ "tie_word_embeddings": false,
48
+ "transformers_version": "4.57.3",
49
+ "use_cache": true,
50
+ "use_sliding_window": false,
51
+ "vocab_size": 151936
52
+ }