Hugging Face's logo

groxaxo
/
DeepSWE-Preview-FP8

Safetensors
qwen3
qwen
deepswe
fp8
quantized
code
coding
ai
software-engineering
rl
derived-from-agentica-org/DeepSWE-Preview
compressed-tensors
Model card Files
xet
Community
groxaxo commited on
Commit
1748d5e
·
verified ·
1 Parent(s): 8c328ac

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +142 -0
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
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": 25600,
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
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention"
79
+ ],
80
+ "max_position_embeddings": 40960,
81
+ "max_window_layers": 64,
82
+ "model_type": "qwen3",
83
+ "num_attention_heads": 64,
84
+ "num_hidden_layers": 64,
85
+ "num_key_value_heads": 8,
86
+ "pad_token_id": 151643,
87
+ "quantization_config": {
88
+ "config_groups": {
89
+ "group_0": {
90
+ "format": "float-quantized",
91
+ "input_activations": {
92
+ "actorder": null,
93
+ "block_structure": null,
94
+ "dynamic": false,
95
+ "group_size": null,
96
+ "num_bits": 8,
97
+ "observer": "minmax",
98
+ "observer_kwargs": {},
99
+ "strategy": "tensor",
100
+ "symmetric": true,
101
+ "type": "float"
102
+ },
103
+ "output_activations": null,
104
+ "targets": [
105
+ "Linear"
106
+ ],
107
+ "weights": {
108
+ "actorder": null,
109
+ "block_structure": null,
110
+ "dynamic": false,
111
+ "group_size": null,
112
+ "num_bits": 8,
113
+ "observer": "minmax",
114
+ "observer_kwargs": {},
115
+ "strategy": "tensor",
116
+ "symmetric": true,
117
+ "type": "float"
118
+ }
119
+ }
120
+ },
121
+ "format": "float-quantized",
122
+ "global_compression_ratio": null,
123
+ "ignore": [
124
+ "lm_head"
125
+ ],
126
+ "kv_cache_scheme": null,
127
+ "quant_method": "compressed-tensors",
128
+ "quantization_status": "compressed",
129
+ "sparsity_config": {},
130
+ "transform_config": {},
131
+ "version": "0.11.1.a20250828"
132
+ },
133
+ "rms_norm_eps": 1e-06,
134
+ "rope_scaling": null,
135
+ "rope_theta": 1000000,
136
+ "sliding_window": null,
137
+ "tie_word_embeddings": false,
138
+ "transformers_version": "4.56.0",
139
+ "use_cache": true,
140
+ "use_sliding_window": false,
141
+ "vocab_size": 151936
142
+ }