Hugging Face's logo

inclusionAI
/
Ling-3.0-flash-dspark

Text Generation
Transformers
Safetensors
qwen3
speculative-decoding
dspark
dflash
specforge
sglang
text-generation-inference
Model card Files
xet
 Community
2
michael-qiu commited on
Commit
3f0e4e1
·
verified ·
1 Parent(s): c2e3643

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. config.json +191 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LingDSparkModel"
4
+ ],
5
+ "model_type": "qwen3",
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "block_size": 8,
9
+ "confidence_head_with_markov": true,
10
+ "dtype": "bfloat16",
11
+ "embedding_dropout": 0.0,
12
+ "enable_confidence_head": true,
13
+ "eos_token_id": 156895,
14
+ "expert_swiglu_limit_list": [
15
+ 0,
16
+ 0,
17
+ 0,
18
+ 0,
19
+ 0,
20
+ 0,
21
+ 0,
22
+ 0,
23
+ 0,
24
+ 0,
25
+ 0,
26
+ 0,
27
+ 0,
28
+ 0,
29
+ 0,
30
+ 0,
31
+ 0,
32
+ 0,
33
+ 0,
34
+ 0,
35
+ 0,
36
+ 0,
37
+ 0,
38
+ 0,
39
+ 0,
40
+ 0,
41
+ 0,
42
+ 0,
43
+ 0,
44
+ 0,
45
+ 0,
46
+ 0,
47
+ 0,
48
+ 0,
49
+ 0,
50
+ 4,
51
+ 4,
52
+ 4,
53
+ 4,
54
+ 4,
55
+ 4,
56
+ 4
57
+ ],
58
+ "first_k_dense_replace": 2,
59
+ "gated_attention_proj_granularity_type": "head_wise",
60
+ "group_norm_size": 1,
61
+ "head_dim": 128,
62
+ "hidden_act": "silu",
63
+ "hidden_size": 2560,
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 6144,
66
+ "kda_lower_bound": -5.0,
67
+ "kda_safe_gate": true,
68
+ "kv_lora_rank": 512,
69
+ "layer_group_size": 6,
70
+ "layer_types": [
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention"
76
+ ],
77
+ "linear_silu": true,
78
+ "markov_head_type": "vanilla",
79
+ "markov_rank": 256,
80
+ "mask_token_id": 156892,
81
+ "max_position_embeddings": 131072,
82
+ "max_window_layers": 20,
83
+ "moe_intermediate_size": 768,
84
+ "moe_router_enable_expert_bias": true,
85
+ "moe_shared_expert_intermediate_size": 768,
86
+ "mtp_loss_scaling_factor": 0,
87
+ "mtp_use_kda": false,
88
+ "n_group": 8,
89
+ "no_kda_lora": true,
90
+ "norm_topk_prob": true,
91
+ "num_anchors": 512,
92
+ "num_attention_heads": 32,
93
+ "num_experts": 512,
94
+ "num_experts_per_tok": 8,
95
+ "num_hidden_layers": 5,
96
+ "num_key_value_heads": 32,
97
+ "num_kv_heads_for_linear_attn": 0,
98
+ "num_nextn_predict_layers": 1,
99
+ "num_shared_experts": 1,
100
+ "num_target_layers": 42,
101
+ "output_dropout": 0.0,
102
+ "output_router_logits": false,
103
+ "pad_token_id": 156892,
104
+ "partial_rotary_factor": 1.0,
105
+ "q_lora_rank": null,
106
+ "qk_head_dim": 192,
107
+ "qk_nope_head_dim": 128,
108
+ "qk_rope_head_dim": 64,
109
+ "rms_norm_eps": 1e-06,
110
+ "rope_interleave": true,
111
+ "rope_parameters": {
112
+ "partial_rotary_factor": 1.0,
113
+ "rope_theta": 6000000.0,
114
+ "rope_type": "default"
115
+ },
116
+ "rope_theta": 6000000,
117
+ "rotary_dim": 64,
118
+ "routed_scaling_factor": 2.5,
119
+ "router_dtype": "fp32",
120
+ "scale_router_input": false,
121
+ "score_function": "sigmoid",
122
+ "scoring_func": "sigmoid",
123
+ "seq_aux": true,
124
+ "share_expert_swiglu_limit_list": [
125
+ 0,
126
+ 0,
127
+ 0,
128
+ 0,
129
+ 0,
130
+ 0,
131
+ 0,
132
+ 0,
133
+ 0,
134
+ 0,
135
+ 0,
136
+ 0,
137
+ 0,
138
+ 0,
139
+ 0,
140
+ 0,
141
+ 0,
142
+ 0,
143
+ 0,
144
+ 0,
145
+ 0,
146
+ 0,
147
+ 0,
148
+ 0,
149
+ 0,
150
+ 0,
151
+ 0,
152
+ 0,
153
+ 0,
154
+ 0,
155
+ 0,
156
+ 0,
157
+ 0,
158
+ 0,
159
+ 5,
160
+ 5,
161
+ 5,
162
+ 5,
163
+ 5,
164
+ 5,
165
+ 7,
166
+ 7
167
+ ],
168
+ "short_conv_kernel_size": 4,
169
+ "sliding_window": null,
170
+ "target_layer_ids": [
171
+ 1,
172
+ 11,
173
+ 23,
174
+ 29,
175
+ 35
176
+ ],
177
+ "tie_word_embeddings": false,
178
+ "topk_group": 4,
179
+ "topk_method": "noaux_tc",
180
+ "transformers_version": "5.12.1",
181
+ "up_proj_norm": false,
182
+ "use_bias": false,
183
+ "use_kda_lora": false,
184
+ "use_mla_nope": false,
185
+ "use_nGPT": false,
186
+ "use_qk_norm": true,
187
+ "use_qkv_bias": false,
188
+ "v_head_dim": 128,
189
+ "value_norm": false,
190
+ "vocab_size": 157184
191
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0885659804b3e4460f4bcd50c292923ea4f60e5a83745f96ff3d0736a5e5ddb5
3
+ size 2727422642