Hugging Face's logo

SF-Foundation
/
FlashTopic-14B-FP8-0915

Safetensors
qwen3
compressed-tensors
Model card Files
xet
Community
SF-Foundation commited on
Commit
9ed0b27
·
verified ·
1 Parent(s): 3bfb8a2

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +118 -0
config.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 5120,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 17408,
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
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention"
56
+ ],
57
+ "max_position_embeddings": 40960,
58
+ "max_window_layers": 40,
59
+ "model_type": "qwen3",
60
+ "num_attention_heads": 40,
61
+ "num_hidden_layers": 40,
62
+ "num_key_value_heads": 8,
63
+ "quantization_config": {
64
+ "config_groups": {
65
+ "group_0": {
66
+ "format": "float-quantized",
67
+ "input_activations": {
68
+ "actorder": null,
69
+ "block_structure": null,
70
+ "dynamic": true,
71
+ "group_size": null,
72
+ "num_bits": 8,
73
+ "observer": null,
74
+ "observer_kwargs": {},
75
+ "strategy": "token",
76
+ "symmetric": true,
77
+ "type": "float"
78
+ },
79
+ "output_activations": null,
80
+ "targets": [
81
+ "Linear"
82
+ ],
83
+ "weights": {
84
+ "actorder": null,
85
+ "block_structure": null,
86
+ "dynamic": false,
87
+ "group_size": null,
88
+ "num_bits": 8,
89
+ "observer": "minmax",
90
+ "observer_kwargs": {},
91
+ "strategy": "channel",
92
+ "symmetric": true,
93
+ "type": "float"
94
+ }
95
+ }
96
+ },
97
+ "format": "float-quantized",
98
+ "global_compression_ratio": null,
99
+ "ignore": [
100
+ "lm_head"
101
+ ],
102
+ "kv_cache_scheme": null,
103
+ "quant_method": "compressed-tensors",
104
+ "quantization_status": "compressed",
105
+ "sparsity_config": {},
106
+ "transform_config": {},
107
+ "version": "0.11.0"
108
+ },
109
+ "rms_norm_eps": 1e-06,
110
+ "rope_scaling": null,
111
+ "rope_theta": 1000000,
112
+ "sliding_window": null,
113
+ "tie_word_embeddings": false,
114
+ "transformers_version": "4.56.1",
115
+ "use_cache": true,
116
+ "use_sliding_window": false,
117
+ "vocab_size": 152660
118
+ }