dangell7 commited on
Commit
2b07f18
·
verified ·
1 Parent(s): 544dcf2

Fix config: use Qwen3_5ForConditionalGeneration wrapper (canonical arch for Qwen3.5 family, required by sglang)

Browse files
Files changed (2) hide show
  1. config.json +133 -113
  2. processor_config.json +63 -0
config.json CHANGED
@@ -1,115 +1,135 @@
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": "5.5.3",
113
- "use_cache": false,
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
+ "dtype": "bfloat16",
12
+ "eos_token_id": 248044,
13
+ "full_attention_interval": 4,
14
+ "head_dim": 256,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 5120,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 17408,
19
+ "layer_types": [
20
+ "linear_attention",
21
+ "linear_attention",
22
+ "linear_attention",
23
+ "full_attention",
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "full_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "full_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "full_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "full_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "full_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "full_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "full_attention",
52
+ "linear_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "full_attention",
56
+ "linear_attention",
57
+ "linear_attention",
58
+ "linear_attention",
59
+ "full_attention",
60
+ "linear_attention",
61
+ "linear_attention",
62
+ "linear_attention",
63
+ "full_attention",
64
+ "linear_attention",
65
+ "linear_attention",
66
+ "linear_attention",
67
+ "full_attention",
68
+ "linear_attention",
69
+ "linear_attention",
70
+ "linear_attention",
71
+ "full_attention",
72
+ "linear_attention",
73
+ "linear_attention",
74
+ "linear_attention",
75
+ "full_attention",
76
+ "linear_attention",
77
+ "linear_attention",
78
+ "linear_attention",
79
+ "full_attention",
80
+ "linear_attention",
81
+ "linear_attention",
82
+ "linear_attention",
83
+ "full_attention"
84
+ ],
85
+ "linear_conv_kernel_dim": 4,
86
+ "linear_key_head_dim": 128,
87
+ "linear_num_key_heads": 16,
88
+ "linear_num_value_heads": 48,
89
+ "linear_value_head_dim": 128,
90
+ "max_position_embeddings": 262144,
91
+ "mlp_only_layers": [],
92
+ "model_type": "qwen3_5_text",
93
+ "mtp_num_hidden_layers": 1,
94
+ "mtp_use_dedicated_embeddings": false,
95
+ "num_attention_heads": 24,
96
+ "num_hidden_layers": 64,
97
+ "num_key_value_heads": 4,
98
+ "rms_norm_eps": 1e-06,
99
+ "use_cache": true,
100
+ "vocab_size": 248320,
101
+ "mamba_ssm_dtype": "float32",
102
+ "rope_parameters": {
103
+ "mrope_interleaved": true,
104
+ "mrope_section": [
105
+ 11,
106
+ 11,
107
+ 10
108
+ ],
109
+ "rope_type": "default",
110
+ "rope_theta": 10000000,
111
+ "partial_rotary_factor": 0.25
112
+ }
113
+ },
114
+ "tie_word_embeddings": false,
115
+ "transformers_version": "4.57.0.dev0",
116
+ "video_token_id": 248057,
117
+ "vision_config": {
118
+ "deepstack_visual_indexes": [],
119
+ "depth": 27,
120
+ "hidden_act": "gelu_pytorch_tanh",
121
+ "hidden_size": 1152,
122
+ "in_channels": 3,
123
+ "initializer_range": 0.02,
124
+ "intermediate_size": 4304,
125
+ "model_type": "qwen3_5",
126
+ "num_heads": 16,
127
+ "num_position_embeddings": 2304,
128
+ "out_hidden_size": 5120,
129
+ "patch_size": 16,
130
+ "spatial_merge_size": 2,
131
+ "temporal_patch_size": 2
132
+ },
133
+ "vision_end_token_id": 248054,
134
+ "vision_start_token_id": 248053
135
+ }
processor_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Qwen2VLImageProcessorFast",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "merge_size": 2,
20
+ "patch_size": 16,
21
+ "resample": 3,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 16777216,
25
+ "shortest_edge": 65536
26
+ },
27
+ "temporal_patch_size": 2
28
+ },
29
+ "processor_class": "Qwen3VLProcessor",
30
+ "video_processor": {
31
+ "data_format": "channels_first",
32
+ "default_to_square": true,
33
+ "do_convert_rgb": true,
34
+ "do_normalize": true,
35
+ "do_rescale": true,
36
+ "do_resize": true,
37
+ "do_sample_frames": true,
38
+ "fps": 2,
39
+ "image_mean": [
40
+ 0.5,
41
+ 0.5,
42
+ 0.5
43
+ ],
44
+ "image_std": [
45
+ 0.5,
46
+ 0.5,
47
+ 0.5
48
+ ],
49
+ "max_frames": 768,
50
+ "merge_size": 2,
51
+ "min_frames": 4,
52
+ "patch_size": 16,
53
+ "resample": 3,
54
+ "rescale_factor": 0.00392156862745098,
55
+ "return_metadata": false,
56
+ "size": {
57
+ "longest_edge": 25165824,
58
+ "shortest_edge": 4096
59
+ },
60
+ "temporal_patch_size": 2,
61
+ "video_processor_type": "Qwen3VLVideoProcessor"
62
+ }
63
+ }