Hugging Face's logo

wind77
/
424

Safetensors
qwen3_5
Model card Files
xet
 Community
wind77 commited on
Commit
17580cf
·
verified ·
1 Parent(s): b0ae8f5

Fix config.json: restore nested text_config structure (was incorrectly flattened)

Browse files
Files changed (1) hide show
  1. config.json +84 -90
config.json CHANGED
@@ -1,98 +1,92 @@
1
  {
2
- "transformers_version": "5.5.3",
3
  "architectures": [
4
  "Qwen3_5ForConditionalGeneration"
5
  ],
6
- "output_hidden_states": false,
7
- "return_dict": true,
8
- "dtype": "bfloat16",
9
- "chunk_size_feed_forward": 0,
10
- "is_encoder_decoder": false,
11
- "id2label": {
12
- "0": "LABEL_0",
13
- "1": "LABEL_1"
14
- },
15
- "label2id": {
16
- "LABEL_0": 0,
17
- "LABEL_1": 1
18
- },
19
- "problem_type": null,
20
- "vocab_size": 248320,
21
- "hidden_size": 2560,
22
- "intermediate_size": 9216,
23
- "num_hidden_layers": 32,
24
- "num_attention_heads": 16,
25
- "num_key_value_heads": 4,
26
- "hidden_act": "silu",
27
- "max_position_embeddings": 262144,
28
- "initializer_range": 0.02,
29
- "rms_norm_eps": 1e-06,
30
- "use_cache": false,
31
- "tie_word_embeddings": false,
32
- "rope_parameters": {
33
- "mrope_interleaved": true,
34
- "mrope_section": [
35
- 11,
36
- 11,
37
- 10
38
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  "partial_rotary_factor": 0.25,
40
- "rope_theta": 10000000,
41
- "rope_type": "default"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  },
43
- "attention_bias": false,
44
- "attention_dropout": 0.0,
45
- "head_dim": 256,
46
- "linear_conv_kernel_dim": 4,
47
- "linear_key_head_dim": 128,
48
- "linear_value_head_dim": 128,
49
- "linear_num_key_heads": 16,
50
- "linear_num_value_heads": 32,
51
- "layer_types": [
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
- "pad_token_id": 248044,
86
- "bos_token_id": null,
87
- "eos_token_id": 248046,
88
- "_name_or_path": "tom9491/distil-32",
89
- "attn_output_gate": true,
90
- "full_attention_interval": 4,
91
- "mamba_ssm_dtype": "float32",
92
- "mlp_only_layers": [],
93
- "model_type": "qwen3_5",
94
- "mtp_num_hidden_layers": 1,
95
- "mtp_use_dedicated_embeddings": false,
96
- "partial_rotary_factor": 0.25,
97
- "output_attentions": false
98
  }
 
1
  {
 
2
  "architectures": [
3
  "Qwen3_5ForConditionalGeneration"
4
  ],
5
+ "model_type": "qwen3_5",
6
+ "text_config": {
7
+ "architectures": [
8
+ "Qwen3_5ForCausalLM"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  ],
10
+ "attention_bias": false,
11
+ "attention_dropout": 0.0,
12
+ "attn_output_gate": true,
13
+ "bos_token_id": null,
14
+ "dtype": "bfloat16",
15
+ "eos_token_id": 248046,
16
+ "full_attention_interval": 4,
17
+ "head_dim": 256,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 2560,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 9216,
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
+ ],
56
+ "linear_conv_kernel_dim": 4,
57
+ "linear_key_head_dim": 128,
58
+ "linear_num_key_heads": 16,
59
+ "linear_num_value_heads": 32,
60
+ "linear_value_head_dim": 128,
61
+ "mamba_ssm_dtype": "float32",
62
+ "max_position_embeddings": 262144,
63
+ "mlp_only_layers": [],
64
+ "model_type": "qwen3_5_text",
65
+ "mtp_num_hidden_layers": 1,
66
+ "mtp_use_dedicated_embeddings": false,
67
+ "num_attention_heads": 16,
68
+ "num_hidden_layers": 32,
69
+ "num_key_value_heads": 4,
70
+ "pad_token_id": 248044,
71
  "partial_rotary_factor": 0.25,
72
+ "rms_norm_eps": 1e-06,
73
+ "rope_parameters": {
74
+ "mrope_interleaved": true,
75
+ "mrope_section": [
76
+ 11,
77
+ 11,
78
+ 10
79
+ ],
80
+ "partial_rotary_factor": 0.25,
81
+ "rope_theta": 10000000,
82
+ "rope_type": "default"
83
+ },
84
+ "tie_word_embeddings": false,
85
+ "transformers_version": "5.4.0",
86
+ "use_cache": false,
87
+ "vocab_size": 248320
88
  },
89
+ "tie_word_embeddings": false,
90
+ "torch_dtype": "bfloat16",
91
+ "transformers_version": "5.4.0"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92
  }