Cialtion commited on
Commit
f3d6c03
·
verified ·
1 Parent(s): a48d284

Delete config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +0 -103
config.json DELETED
@@ -1,103 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "dtype": "float16",
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": 262144,
54
- "max_window_layers": 36,
55
- "model_type": "qwen3",
56
- "num_attention_heads": 32,
57
- "num_hidden_layers": 36,
58
- "num_key_value_heads": 8,
59
- "quantization_config": {
60
- "config_groups": {
61
- "group_0": {
62
- "format": "pack-quantized",
63
- "input_activations": null,
64
- "output_activations": null,
65
- "targets": [
66
- "Linear"
67
- ],
68
- "weights": {
69
- "actorder": null,
70
- "block_structure": null,
71
- "dynamic": false,
72
- "group_size": 128,
73
- "num_bits": 4,
74
- "observer": "minmax",
75
- "observer_kwargs": {},
76
- "strategy": "group",
77
- "symmetric": false,
78
- "type": "int"
79
- }
80
- }
81
- },
82
- "format": "pack-quantized",
83
- "global_compression_ratio": null,
84
- "ignore": [
85
- "lm_head"
86
- ],
87
- "kv_cache_scheme": null,
88
- "quant_method": "compressed-tensors",
89
- "quantization_status": "compressed",
90
- "sparsity_config": {},
91
- "transform_config": {},
92
- "version": "0.12.2"
93
- },
94
- "rms_norm_eps": 1e-06,
95
- "rope_scaling": null,
96
- "rope_theta": 5000000,
97
- "sliding_window": null,
98
- "tie_word_embeddings": false,
99
- "transformers_version": "4.56.2",
100
- "use_cache": true,
101
- "use_sliding_window": false,
102
- "vocab_size": 151686
103
- }