Gryphe/Pantheon-Reasoning-27B
31137
1{
2 "architectures": [
3 "Qwen3_5ForConditionalGeneration"
4 ],
5 "dtype": "bfloat16",
6 "image_token_id": 248056,
7 "language_model_only": false,
8 "model_type": "qwen3_5",
9 "text_config": {
10 "attention_bias": false,
11 "attention_dropout": 0.0,
12 "attn_output_gate": true,
13 "bos_token_id": 248044,
14 "dtype": "bfloat16",
15 "eos_token_id": 248044,
16 "full_attention_interval": 4,
17 "head_dim": 256,
18 "hidden_act": "silu",
19 "hidden_size": 5120,
20 "initializer_range": 0.02,
21 "intermediate_size": 17408,
22 "layer_types": [
23 "linear_attention",
24 "linear_attention",
25 "linear_attention",
26 "full_attention",
27 "linear_attention",
28 "linear_attention",
29 "linear_attention",
30 "full_attention",
31 "linear_attention",
32 "linear_attention",
33 "linear_attention",
34 "full_attention",
35 "linear_attention",
36 "linear_attention",
37 "linear_attention",
38 "full_attention",
39 "linear_attention",
40 "linear_attention",
41 "linear_attention",
42 "full_attention",
43 "linear_attention",
44 "linear_attention",
45 "linear_attention",
46 "full_attention",
47 "linear_attention",
48 "linear_attention",
49 "linear_attention",
50 "full_attention",
51 "linear_attention",
52 "linear_attention",
53 "linear_attention",
54 "full_attention",
55 "linear_attention",
56 "linear_attention",
57 "linear_attention",
58 "full_attention",
59 "linear_attention",
60 "linear_attention",
61 "linear_attention",
62 "full_attention",
63 "linear_attention",
64 "linear_attention",
65 "linear_attention",
66 "full_attention",
67 "linear_attention",
68 "linear_attention",
69 "linear_attention",
70 "full_attention",
71 "linear_attention",
72 "linear_attention",
73 "linear_attention",
74 "full_attention",
75 "linear_attention",
76 "linear_attention",
77 "linear_attention",
78 "full_attention",
79 "linear_attention",
80 "linear_attention",
81 "linear_attention",
82 "full_attention",
83 "linear_attention",
84 "linear_attention",
85 "linear_attention",
86 "full_attention"
87 ],
88 "linear_conv_kernel_dim": 4,
89 "linear_key_head_dim": 128,
90 "linear_num_key_heads": 16,
91 "linear_num_value_heads": 48,
92 "linear_value_head_dim": 128,
93 "mamba_ssm_dtype": "float32",
94 "max_position_embeddings": 262144,
95 "model_type": "qwen3_5_text",
96 "mtp_num_hidden_layers": 1,
97 "mtp_use_dedicated_embeddings": false,
98 "num_attention_heads": 24,
99 "num_hidden_layers": 64,
100 "num_key_value_heads": 4,
101 "output_gate_type": "swish",
102 "pad_token_id": null,
103 "partial_rotary_factor": 0.25,
104 "rms_norm_eps": 1e-06,
105 "rope_parameters": {
106 "mrope_interleaved": true,
107 "mrope_section": [
108 11,
109 11,
110 10
111 ],
112 "partial_rotary_factor": 0.25,
113 "rope_theta": 10000000,
114 "rope_type": "default"
115 },
116 "tie_word_embeddings": false,
117 "use_cache": true,
118 "vocab_size": 248320
119 },
120 "tie_word_embeddings": false,
121 "transformers_version": "5.8.0",
122 "video_token_id": 248057,
123 "vision_config": {
124 "deepstack_visual_indexes": [],
125 "depth": 27,
126 "dtype": "bfloat16",
127 "hidden_act": "gelu_pytorch_tanh",
128 "hidden_size": 1152,
129 "in_channels": 3,
130 "initializer_range": 0.02,
131 "intermediate_size": 4304,
132 "model_type": "qwen3_5_vision",
133 "num_heads": 16,
134 "num_position_embeddings": 2304,
135 "out_hidden_size": 5120,
136 "patch_size": 16,
137 "spatial_merge_size": 2,
138 "temporal_patch_size": 2
139 },
140 "vision_end_token_id": 248054,
141 "vision_start_token_id": 248053
142}
143 