LightningCreeper commited on
Commit
56ace14
·
verified ·
1 Parent(s): d77f22e

Add files using upload-large-folder tool

Browse files
Files changed (1) hide show
  1. config.json +98 -0
config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./WIA-9B",
3
+ "architectures": [
4
+ "Qwen3_5ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_output_gate": true,
9
+ "bos_token_id": null,
10
+ "chunk_size_feed_forward": 0,
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 248044,
13
+ "full_attention_interval": 4,
14
+ "head_dim": 256,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 4096,
17
+ "id2label": {
18
+ "0": "LABEL_0",
19
+ "1": "LABEL_1"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 12288,
23
+ "is_encoder_decoder": false,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1
27
+ },
28
+ "layer_types": [
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "full_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "full_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "full_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "full_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "full_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "full_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "full_attention",
57
+ "linear_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "full_attention"
61
+ ],
62
+ "linear_conv_kernel_dim": 4,
63
+ "linear_key_head_dim": 128,
64
+ "linear_num_key_heads": 16,
65
+ "linear_num_value_heads": 32,
66
+ "linear_value_head_dim": 128,
67
+ "mamba_ssm_dtype": "float32",
68
+ "max_position_embeddings": 262144,
69
+ "mlp_only_layers": [],
70
+ "model_type": "qwen3_5_text",
71
+ "mtp_num_hidden_layers": 1,
72
+ "mtp_use_dedicated_embeddings": false,
73
+ "num_attention_heads": 16,
74
+ "num_hidden_layers": 32,
75
+ "num_key_value_heads": 4,
76
+ "output_attentions": false,
77
+ "output_hidden_states": false,
78
+ "pad_token_id": 248044,
79
+ "partial_rotary_factor": 0.25,
80
+ "problem_type": null,
81
+ "return_dict": true,
82
+ "rms_norm_eps": 1e-06,
83
+ "rope_parameters": {
84
+ "mrope_interleaved": true,
85
+ "mrope_section": [
86
+ 11,
87
+ 11,
88
+ 10
89
+ ],
90
+ "partial_rotary_factor": 0.25,
91
+ "rope_theta": 10000000,
92
+ "rope_type": "default"
93
+ },
94
+ "tie_word_embeddings": false,
95
+ "transformers_version": "5.12.1",
96
+ "use_cache": false,
97
+ "vocab_size": 248320
98
+ }