Hugging Face's logo

gitglubber
/
slider_onnx

ONNX
English
qwen3
Model card Files
xet
Community
gitglubber commited on
Commit
709176d
·
verified ·
1 Parent(s): 458a19e

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +76 -76
config.json CHANGED
@@ -1,77 +1,77 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "eos_token_id": 151645,
9
- "head_dim": 128,
10
- "hidden_act": "silu",
11
- "hidden_size": 2560,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 9728,
14
- "layer_types": [
15
- "full_attention",
16
- "full_attention",
17
- "full_attention",
18
- "full_attention",
19
- "full_attention",
20
- "full_attention",
21
- "full_attention",
22
- "full_attention",
23
- "full_attention",
24
- "full_attention",
25
- "full_attention",
26
- "full_attention",
27
- "full_attention",
28
- "full_attention",
29
- "full_attention",
30
- "full_attention",
31
- "full_attention",
32
- "full_attention",
33
- "full_attention",
34
- "full_attention",
35
- "full_attention",
36
- "full_attention",
37
- "full_attention",
38
- "full_attention",
39
- "full_attention",
40
- "full_attention",
41
- "full_attention",
42
- "full_attention",
43
- "full_attention",
44
- "full_attention",
45
- "full_attention",
46
- "full_attention",
47
- "full_attention",
48
- "full_attention",
49
- "full_attention",
50
- "full_attention"
51
- ],
52
- "max_position_embeddings": 40960,
53
- "max_window_layers": 36,
54
- "model_type": "qwen3",
55
- "num_attention_heads": 32,
56
- "num_hidden_layers": 36,
57
- "num_key_value_heads": 8,
58
- "rms_norm_eps": 1e-06,
59
- "rope_scaling": null,
60
- "rope_theta": 1000000,
61
- "sliding_window": null,
62
- "tie_word_embeddings": true,
63
- "torch_dtype": "bfloat16",
64
- "transformers_version": "4.53.0.dev0",
65
- "use_cache": true,
66
- "use_sliding_window": false,
67
- "vocab_size": 151936,
68
- "transformers.js_config": {
69
- "dtype": "q4f16",
70
- "kv_cache_dtype": {
71
- "q4f16": "float16"
72
- },
73
- "use_external_data_format": {
74
- "model_q4f16.onnx": 1
75
- }
76
- }
77
  }
 
1
+ {
2
+ "model_type": "qwen3",
3
+ "architectures": [
4
+ "Qwen3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 151643,
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2560,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 9728,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 40960,
54
+ "max_window_layers": 36,
55
+ "num_attention_heads": 32,
56
+ "num_hidden_layers": 36,
57
+ "num_key_value_heads": 8,
58
+ "rms_norm_eps": 1e-06,
59
+ "rope_scaling": null,
60
+ "rope_theta": 1000000,
61
+ "sliding_window": null,
62
+ "tie_word_embeddings": true,
63
+ "torch_dtype": "bfloat16",
64
+ "transformers_version": "4.53.0.dev0",
65
+ "use_cache": true,
66
+ "use_sliding_window": false,
67
+ "vocab_size": 151936,
68
+ "transformers.js_config": {
69
+ "dtype": "q4f16",
70
+ "kv_cache_dtype": {
71
+ "q4f16": "float16"
72
+ },
73
+ "use_external_data_format": {
74
+ "model_q4f16.onnx": 1
75
+ }
76
+ }
77
  }