config.json
4.8 KB · 170 lines · json Raw
1 {
2 "architectures": [
3 "Qwen3_5ForConditionalGeneration"
4 ],
5 "do_sample": true,
6 "eos_token_id": [
7 248046,
8 248044
9 ],
10 "generation_config": {
11 "bos_token_id": 248044,
12 "do_sample": true,
13 "eos_token_id": [
14 248046,
15 248044
16 ],
17 "pad_token_id": 248044,
18 "temperature": 1.0,
19 "top_k": 20,
20 "top_p": 0.95
21 },
22 "image_token_id": 248056,
23 "language_model_only": false,
24 "model_type": "qwen3_5",
25 "quantization": {
26 "group_size": 64,
27 "bits": 4,
28 "mode": "affine"
29 },
30 "quantization_config": {
31 "group_size": 64,
32 "bits": 4,
33 "mode": "affine"
34 },
35 "temperature": 1.0,
36 "text_config": {
37 "attention_bias": false,
38 "attention_dropout": 0.0,
39 "attn_output_gate": true,
40 "bos_token_id": 248044,
41 "dtype": "bfloat16",
42 "eos_token_id": 248044,
43 "full_attention_interval": 4,
44 "head_dim": 256,
45 "hidden_act": "silu",
46 "hidden_size": 5120,
47 "initializer_range": 0.02,
48 "intermediate_size": 17408,
49 "layer_types": [
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 "linear_attention",
83 "linear_attention",
84 "linear_attention",
85 "full_attention",
86 "linear_attention",
87 "linear_attention",
88 "linear_attention",
89 "full_attention",
90 "linear_attention",
91 "linear_attention",
92 "linear_attention",
93 "full_attention",
94 "linear_attention",
95 "linear_attention",
96 "linear_attention",
97 "full_attention",
98 "linear_attention",
99 "linear_attention",
100 "linear_attention",
101 "full_attention",
102 "linear_attention",
103 "linear_attention",
104 "linear_attention",
105 "full_attention",
106 "linear_attention",
107 "linear_attention",
108 "linear_attention",
109 "full_attention",
110 "linear_attention",
111 "linear_attention",
112 "linear_attention",
113 "full_attention"
114 ],
115 "linear_conv_kernel_dim": 4,
116 "linear_key_head_dim": 128,
117 "linear_num_key_heads": 16,
118 "linear_num_value_heads": 48,
119 "linear_value_head_dim": 128,
120 "mamba_ssm_dtype": "float32",
121 "max_position_embeddings": 262144,
122 "model_type": "qwen3_5_text",
123 "mtp_num_hidden_layers": 1,
124 "mtp_use_dedicated_embeddings": false,
125 "num_attention_heads": 24,
126 "num_hidden_layers": 64,
127 "num_key_value_heads": 4,
128 "output_gate_type": "swish",
129 "pad_token_id": null,
130 "partial_rotary_factor": 0.25,
131 "rms_norm_eps": 1e-06,
132 "rope_parameters": {
133 "mrope_interleaved": true,
134 "mrope_section": [
135 11,
136 11,
137 10
138 ],
139 "partial_rotary_factor": 0.25,
140 "rope_theta": 10000000,
141 "rope_type": "default"
142 },
143 "tie_word_embeddings": false,
144 "use_cache": true,
145 "vocab_size": 248320
146 },
147 "tie_word_embeddings": false,
148 "top_k": 20,
149 "top_p": 0.95,
150 "transformers_version": "5.8.0.dev0",
151 "video_token_id": 248057,
152 "vision_config": {
153 "deepstack_visual_indexes": [],
154 "depth": 27,
155 "hidden_act": "gelu_pytorch_tanh",
156 "hidden_size": 1152,
157 "in_channels": 3,
158 "initializer_range": 0.02,
159 "intermediate_size": 4304,
160 "model_type": "qwen3_5",
161 "num_heads": 16,
162 "num_position_embeddings": 2304,
163 "out_hidden_size": 5120,
164 "patch_size": 16,
165 "spatial_merge_size": 2,
166 "temporal_patch_size": 2
167 },
168 "vision_end_token_id": 248054,
169 "vision_start_token_id": 248053
170 }