Anserwise commited on
Commit
f21391c
·
verified ·
1 Parent(s): dff8872

Fix config: restore qwen3_5 wrapper structure (model.language_model.* weight namespace requires ForConditionalGeneration wrapper)

Browse files
Files changed (1) hide show
  1. config.json +135 -113
config.json CHANGED
@@ -1,115 +1,137 @@
1
  {
2
- "architectures": [
3
- "Qwen3_5ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "attn_output_gate": true,
8
- "bos_token_id": null,
9
- "dtype": "bfloat16",
10
- "eos_token_id": 248044,
11
- "full_attention_interval": 4,
12
- "head_dim": 256,
13
- "hidden_act": "silu",
14
- "hidden_size": 5120,
15
- "initializer_range": 0.02,
16
- "intermediate_size": 17408,
17
- "layer_types": [
18
- "linear_attention",
19
- "linear_attention",
20
- "linear_attention",
21
- "full_attention",
22
- "linear_attention",
23
- "linear_attention",
24
- "linear_attention",
25
- "full_attention",
26
- "linear_attention",
27
- "linear_attention",
28
- "linear_attention",
29
- "full_attention",
30
- "linear_attention",
31
- "linear_attention",
32
- "linear_attention",
33
- "full_attention",
34
- "linear_attention",
35
- "linear_attention",
36
- "linear_attention",
37
- "full_attention",
38
- "linear_attention",
39
- "linear_attention",
40
- "linear_attention",
41
- "full_attention",
42
- "linear_attention",
43
- "linear_attention",
44
- "linear_attention",
45
- "full_attention",
46
- "linear_attention",
47
- "linear_attention",
48
- "linear_attention",
49
- "full_attention",
50
- "linear_attention",
51
- "linear_attention",
52
- "linear_attention",
53
- "full_attention",
54
- "linear_attention",
55
- "linear_attention",
56
- "linear_attention",
57
- "full_attention",
58
- "linear_attention",
59
- "linear_attention",
60
- "linear_attention",
61
- "full_attention",
62
- "linear_attention",
63
- "linear_attention",
64
- "linear_attention",
65
- "full_attention",
66
- "linear_attention",
67
- "linear_attention",
68
- "linear_attention",
69
- "full_attention",
70
- "linear_attention",
71
- "linear_attention",
72
- "linear_attention",
73
- "full_attention",
74
- "linear_attention",
75
- "linear_attention",
76
- "linear_attention",
77
- "full_attention",
78
- "linear_attention",
79
- "linear_attention",
80
- "linear_attention",
81
- "full_attention"
82
- ],
83
- "linear_conv_kernel_dim": 4,
84
- "linear_key_head_dim": 128,
85
- "linear_num_key_heads": 16,
86
- "linear_num_value_heads": 48,
87
- "linear_value_head_dim": 128,
88
- "mamba_ssm_dtype": "float32",
89
- "max_position_embeddings": 262144,
90
- "mlp_only_layers": [],
91
- "model_type": "qwen3_5_text",
92
- "mtp_num_hidden_layers": 1,
93
- "mtp_use_dedicated_embeddings": false,
94
- "num_attention_heads": 24,
95
- "num_hidden_layers": 64,
96
- "num_key_value_heads": 4,
97
- "pad_token_id": null,
98
- "partial_rotary_factor": 0.25,
99
- "rms_norm_eps": 1e-06,
100
- "rope_parameters": {
101
- "mrope_interleaved": true,
102
- "mrope_section": [
103
- 11,
104
- 11,
105
- 10
106
  ],
107
- "partial_rotary_factor": 0.25,
108
- "rope_theta": 10000000,
109
- "rope_type": "default"
110
- },
111
- "tie_word_embeddings": false,
112
- "transformers_version": "5.5.4",
113
- "use_cache": true,
114
- "vocab_size": 248320
115
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  ],
5
+ "image_token_id": 248056,
6
+ "model_type": "qwen3_5",
7
+ "text_config": {
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "attn_output_gate": true,
11
+ "bos_token_id": null,
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": 248044,
14
+ "full_attention_interval": 4,
15
+ "head_dim": 256,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 5120,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 17408,
20
+ "layer_types": [
21
+ "linear_attention",
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "full_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "full_attention",
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
+ "linear_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "full_attention",
65
+ "linear_attention",
66
+ "linear_attention",
67
+ "linear_attention",
68
+ "full_attention",
69
+ "linear_attention",
70
+ "linear_attention",
71
+ "linear_attention",
72
+ "full_attention",
73
+ "linear_attention",
74
+ "linear_attention",
75
+ "linear_attention",
76
+ "full_attention",
77
+ "linear_attention",
78
+ "linear_attention",
79
+ "linear_attention",
80
+ "full_attention",
81
+ "linear_attention",
82
+ "linear_attention",
83
+ "linear_attention",
84
+ "full_attention"
85
+ ],
86
+ "linear_conv_kernel_dim": 4,
87
+ "linear_key_head_dim": 128,
88
+ "linear_num_key_heads": 16,
89
+ "linear_num_value_heads": 48,
90
+ "linear_value_head_dim": 128,
91
+ "mamba_ssm_dtype": "float32",
92
+ "max_position_embeddings": 262144,
93
+ "mlp_only_layers": [],
94
+ "model_type": "qwen3_5_text",
95
+ "mtp_num_hidden_layers": 1,
96
+ "mtp_use_dedicated_embeddings": false,
97
+ "num_attention_heads": 24,
98
+ "num_hidden_layers": 64,
99
+ "num_key_value_heads": 4,
100
+ "pad_token_id": null,
101
+ "rms_norm_eps": 1e-06,
102
+ "rope_parameters": {
103
+ "mrope_interleaved": true,
104
+ "mrope_section": [
105
+ 11,
106
+ 11,
107
+ 10
108
+ ],
109
+ "partial_rotary_factor": 0.25,
110
+ "rope_theta": 10000000,
111
+ "rope_type": "default"
112
+ },
113
+ "use_cache": true,
114
+ "vocab_size": 248320
115
+ },
116
+ "tie_word_embeddings": false,
117
+ "transformers_version": "4.57.0.dev0",
118
+ "video_token_id": 248057,
119
+ "vision_config": {
120
+ "deepstack_visual_indexes": [],
121
+ "depth": 27,
122
+ "hidden_act": "gelu_pytorch_tanh",
123
+ "hidden_size": 1152,
124
+ "in_channels": 3,
125
+ "initializer_range": 0.02,
126
+ "intermediate_size": 4304,
127
+ "model_type": "qwen3_5",
128
+ "num_heads": 16,
129
+ "num_position_embeddings": 2304,
130
+ "out_hidden_size": 5120,
131
+ "patch_size": 16,
132
+ "spatial_merge_size": 2,
133
+ "temporal_patch_size": 2
134
+ },
135
+ "vision_end_token_id": 248054,
136
+ "vision_start_token_id": 248053
137
+ }