Hugging Face's logo

inclusionAI
/
Ling-3.0-flash-VL-int4

Image-Text-to-Text
Safetensors
bailing_moe_v3_vl
conversational
custom_code
compressed-tensors
Model card Files
xet
 Community
3

Update config.json

#2
by vitoyy - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+14
-127
Files changed (1) hide show
  1. config.json +14 -127
config.json CHANGED
@@ -15,11 +15,7 @@
15
  "video_token_id": 156909,
16
  "vision_start_token_id": 157158,
17
  "vision_end_token_id": 157159,
18
- "mrope_section": [
19
- 8,
20
- 12,
21
- 12
22
- ],
23
  "text_config": {
24
  "image_patch_token": 157157,
25
  "video_patch_token": 156909,
@@ -74,130 +70,21 @@
74
  "kda_lower_bound": -5.0,
75
  "norm_topk_prob": true,
76
  "expert_swiglu_limit_list": [
77
- 0,
78
- 0,
79
- 0,
80
- 0,
81
- 0,
82
- 0,
83
- 0,
84
- 0,
85
- 0,
86
- 0,
87
- 0,
88
- 0,
89
- 0,
90
- 0,
91
- 0,
92
- 0,
93
- 0,
94
- 0,
95
- 0,
96
- 0,
97
- 0,
98
- 0,
99
- 0,
100
- 0,
101
- 0,
102
- 0,
103
- 0,
104
- 0,
105
- 0,
106
- 0,
107
- 0,
108
- 0,
109
- 0,
110
- 0,
111
- 0,
112
- 4,
113
- 4,
114
- 4,
115
- 4,
116
- 4,
117
- 4,
118
- 4
119
  ],
120
  "share_expert_swiglu_limit_list": [
121
- 0,
122
- 0,
123
- 0,
124
- 0,
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
- 5,
156
- 5,
157
- 5,
158
- 5,
159
- 5,
160
- 5,
161
- 7,
162
- 7
163
- ],
164
- "quantization_config": {
165
- "config_groups": {
166
- "group_0": {
167
- "input_activations": null,
168
- "output_activations": null,
169
- "targets": [
170
- "Linear"
171
- ],
172
- "weights": {
173
- "actorder": null,
174
- "block_structure": null,
175
- "dynamic": false,
176
- "group_size": 32,
177
- "num_bits": 4,
178
- "observer": "minmax",
179
- "observer_kwargs": {},
180
- "strategy": "group",
181
- "symmetric": true,
182
- "type": "int"
183
- }
184
- }
185
- },
186
- "format": "pack-quantized",
187
- "global_compression_ratio": null,
188
- "ignore": [
189
- "re:.*lm_head.*",
190
- "re:.*self_attn.*",
191
- "re:.*attention.*",
192
- "re:.*(mlp|shared_experts)\\.(gate|up|gate_up|down|eh)_proj.*",
193
- "re:.*layers\\.\\d+\\.(gate|up|gate_up|down|eh)_proj.*"
194
- ],
195
- "kv_cache_scheme": null,
196
- "quant_method": "compressed-tensors",
197
- "quantization_status": "compressed",
198
- "sparsity_config": {},
199
- "transform_config": {}
200
- }
201
  },
202
  "vision_config": {
203
  "model_type": "qwen3_moe_vit",
 
15
  "video_token_id": 156909,
16
  "vision_start_token_id": 157158,
17
  "vision_end_token_id": 157159,
18
+ "mrope_section": [8, 12, 12],
 
 
 
 
19
  "text_config": {
20
  "image_patch_token": 157157,
21
  "video_patch_token": 156909,
 
70
  "kda_lower_bound": -5.0,
71
  "norm_topk_prob": true,
72
  "expert_swiglu_limit_list": [
73
+ 0, 0, 0, 0, 0, 0, 0,
74
+ 0, 0, 0, 0, 0, 0, 0,
75
+ 0, 0, 0, 0, 0, 0, 0,
76
+ 0, 0, 0, 0, 0, 0, 0,
77
+ 0, 0, 0, 0, 0, 0, 0,
78
+ 4, 4, 4, 4, 4, 4, 4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79
  ],
80
  "share_expert_swiglu_limit_list": [
81
+ 0, 0, 0, 0, 0, 0, 0,
82
+ 0, 0, 0, 0, 0, 0, 0,
83
+ 0, 0, 0, 0, 0, 0, 0,
84
+ 0, 0, 0, 0, 0, 0, 0,
85
+ 0, 0, 0, 0, 0, 0,
86
+ 5, 5, 5, 5, 5, 5, 7, 7
87
+ ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  },
89
  "vision_config": {
90
  "model_type": "qwen3_moe_vit",