Hugging Face's logo

caphe
/
panda

Image-Text-to-Text
Transformers
Safetensors
qwen3_5_moe
conversational
Model card Files
xet
 Community
caphe commited on
Commit
6ccb933
·
verified ·
1 Parent(s): 00e014e

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +112 -86
config.json CHANGED
@@ -1,95 +1,121 @@
1
  {
2
  "architectures": [
3
- "Qwen3_5MoeForCausalLM"
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": 248046,
11
- "full_attention_interval": 4,
12
- "head_dim": 256,
13
- "hidden_act": "silu",
14
- "hidden_size": 2048,
15
- "initializer_range": 0.02,
16
- "layer_types": [
17
- "linear_attention",
18
- "linear_attention",
19
- "linear_attention",
20
- "full_attention",
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
- ],
58
- "linear_conv_kernel_dim": 4,
59
- "linear_key_head_dim": 128,
60
- "linear_num_key_heads": 16,
61
- "linear_num_value_heads": 32,
62
- "linear_value_head_dim": 128,
63
- "mamba_ssm_dtype": "float32",
64
- "max_position_embeddings": 262144,
65
- "model_type": "qwen3_5_moe_text",
66
- "moe_intermediate_size": 512,
67
- "mtp_num_hidden_layers": 1,
68
- "mtp_use_dedicated_embeddings": false,
69
- "num_attention_heads": 16,
70
- "num_experts": 256,
71
- "num_experts_per_tok": 8,
72
- "num_hidden_layers": 40,
73
- "num_key_value_heads": 2,
74
- "output_router_logits": false,
75
- "pad_token_id": 248044,
76
- "partial_rotary_factor": 0.25,
77
- "rms_norm_eps": 1e-06,
78
- "rope_parameters": {
79
- "mrope_interleaved": true,
80
- "mrope_section": [
81
- 11,
82
- 11,
83
- 10
84
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
  "partial_rotary_factor": 0.25,
86
- "rope_theta": 10000000,
87
- "rope_type": "default"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  },
89
- "router_aux_loss_coef": 0.001,
90
- "shared_expert_intermediate_size": 512,
91
  "tie_word_embeddings": false,
92
- "transformers_version": "5.7.0",
93
- "use_cache": false,
94
- "vocab_size": 248320
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95
  }
 
1
  {
2
  "architectures": [
3
+ "Qwen3_5MoeForConditionalGeneration"
4
  ],
 
 
 
 
5
  "dtype": "bfloat16",
6
+ "image_token_id": 248056,
7
+ "model_type": "qwen3_5_moe",
8
+ "text_config": {
9
+ "attention_bias": false,
10
+ "attention_dropout": 0.0,
11
+ "attn_output_gate": true,
12
+ "bos_token_id": null,
13
+ "dtype": "bfloat16",
14
+ "eos_token_id": 248046,
15
+ "full_attention_interval": 4,
16
+ "head_dim": 256,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 2048,
19
+ "initializer_range": 0.02,
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
  ],
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
+ "model_type": "qwen3_5_moe_text",
70
+ "moe_intermediate_size": 512,
71
+ "mtp_num_hidden_layers": 1,
72
+ "mtp_use_dedicated_embeddings": false,
73
+ "num_attention_heads": 16,
74
+ "num_experts": 256,
75
+ "num_experts_per_tok": 8,
76
+ "num_hidden_layers": 40,
77
+ "num_key_value_heads": 2,
78
+ "output_router_logits": false,
79
+ "pad_token_id": 248044,
80
  "partial_rotary_factor": 0.25,
81
+ "rms_norm_eps": 1e-06,
82
+ "rope_parameters": {
83
+ "mrope_interleaved": true,
84
+ "mrope_section": [
85
+ 11,
86
+ 11,
87
+ 10
88
+ ],
89
+ "partial_rotary_factor": 0.25,
90
+ "rope_theta": 10000000,
91
+ "rope_type": "default"
92
+ },
93
+ "router_aux_loss_coef": 0.001,
94
+ "shared_expert_intermediate_size": 512,
95
+ "tie_word_embeddings": false,
96
+ "use_cache": false,
97
+ "vocab_size": 248320
98
  },
 
 
99
  "tie_word_embeddings": false,
100
+ "transformers_version": "5.13.0",
101
+ "video_token_id": 248057,
102
+ "vision_config": {
103
+ "deepstack_visual_indexes": [],
104
+ "depth": 27,
105
+ "dtype": "bfloat16",
106
+ "hidden_act": "gelu_pytorch_tanh",
107
+ "hidden_size": 1152,
108
+ "in_channels": 3,
109
+ "initializer_range": 0.02,
110
+ "intermediate_size": 4304,
111
+ "model_type": "qwen3_5_moe_vision",
112
+ "num_heads": 16,
113
+ "num_position_embeddings": 2304,
114
+ "out_hidden_size": 2048,
115
+ "patch_size": 16,
116
+ "spatial_merge_size": 2,
117
+ "temporal_patch_size": 2
118
+ },
119
+ "vision_end_token_id": 248054,
120
+ "vision_start_token_id": 248053
121
  }