warshanks commited on
Commit
f10e489
·
verified ·
1 Parent(s): c7896cd

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +103 -0
config.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 17408,
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
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention"
55
+ ],
56
+ "max_position_embeddings": 40960,
57
+ "max_window_layers": 40,
58
+ "model_type": "qwen3",
59
+ "num_attention_heads": 40,
60
+ "num_hidden_layers": 40,
61
+ "num_key_value_heads": 8,
62
+ "quantization_config": {
63
+ "config_groups": {
64
+ "group_0": {
65
+ "input_activations": null,
66
+ "output_activations": null,
67
+ "targets": [
68
+ "Linear"
69
+ ],
70
+ "weights": {
71
+ "actorder": null,
72
+ "block_structure": null,
73
+ "dynamic": false,
74
+ "group_size": 128,
75
+ "num_bits": 4,
76
+ "observer": "minmax",
77
+ "observer_kwargs": {},
78
+ "strategy": "group",
79
+ "symmetric": false,
80
+ "type": "int"
81
+ }
82
+ }
83
+ },
84
+ "format": "pack-quantized",
85
+ "global_compression_ratio": null,
86
+ "ignore": [
87
+ "lm_head"
88
+ ],
89
+ "kv_cache_scheme": null,
90
+ "quant_method": "compressed-tensors",
91
+ "quantization_status": "compressed"
92
+ },
93
+ "rms_norm_eps": 1e-06,
94
+ "rope_scaling": null,
95
+ "rope_theta": 1000000,
96
+ "sliding_window": null,
97
+ "tie_word_embeddings": false,
98
+ "torch_dtype": "bfloat16",
99
+ "transformers_version": "4.54.1",
100
+ "use_cache": true,
101
+ "use_sliding_window": false,
102
+ "vocab_size": 151936
103
+ }