Hugging Face's logo

Intel
/
Qwen3-30B-A3B-FP8-Test-Only

Safetensors
qwen3_moe
compressed-tensors
Model card Files
xet
Community
lvkaokao commited on
Commit
d4be7a9
·
1 Parent(s): af084cb

init model files.

Browse files
Files changed (8) hide show
  1. README.md +2 -0
  2. added_tokens.json +3 -28
  3. config.json +3 -132
  4. generation_config.json +3 -13
  5. model.safetensors.index.json +0 -0
  6. special_tokens_map.json +3 -31
  7. tokenizer_config.json +3 -239
  8. vocab.json +0 -0
README.md CHANGED
@@ -1,3 +1,5 @@
1
  ---
2
  license: apache-2.0
3
  ---
 
 
 
1
  ---
2
  license: apache-2.0
3
  ---
4
+
5
+ FP8 static quantized model with compressored tensors. per-channel weight and per-tensor activation.
added_tokens.json CHANGED
@@ -1,28 +1,3 @@
1
- {
2
- "</think>": 151668,
3
- "</tool_call>": 151658,
4
- "</tool_response>": 151666,
5
- "<think>": 151667,
6
- "<tool_call>": 151657,
7
- "<tool_response>": 151665,
8
- "<|box_end|>": 151649,
9
- "<|box_start|>": 151648,
10
- "<|endoftext|>": 151643,
11
- "<|file_sep|>": 151664,
12
- "<|fim_middle|>": 151660,
13
- "<|fim_pad|>": 151662,
14
- "<|fim_prefix|>": 151659,
15
- "<|fim_suffix|>": 151661,
16
- "<|im_end|>": 151645,
17
- "<|im_start|>": 151644,
18
- "<|image_pad|>": 151655,
19
- "<|object_ref_end|>": 151647,
20
- "<|object_ref_start|>": 151646,
21
- "<|quad_end|>": 151651,
22
- "<|quad_start|>": 151650,
23
- "<|repo_name|>": 151663,
24
- "<|video_pad|>": 151656,
25
- "<|vision_end|>": 151653,
26
- "<|vision_pad|>": 151654,
27
- "<|vision_start|>": 151652
28
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
3
+ size 707
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -1,132 +1,3 @@
1
- {
2
- "architectures": [
3
- "Qwen3MoeForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "decoder_sparse_step": 1,
9
- "dtype": "bfloat16",
10
- "eos_token_id": 151645,
11
- "head_dim": 128,
12
- "hidden_act": "silu",
13
- "hidden_size": 2048,
14
- "initializer_range": 0.02,
15
- "intermediate_size": 6144,
16
- "max_position_embeddings": 40960,
17
- "max_window_layers": 48,
18
- "mlp_only_layers": [],
19
- "model_type": "qwen3_moe",
20
- "moe_intermediate_size": 768,
21
- "norm_topk_prob": true,
22
- "num_attention_heads": 32,
23
- "num_experts": 128,
24
- "num_experts_per_tok": 8,
25
- "num_hidden_layers": 48,
26
- "num_key_value_heads": 4,
27
- "output_router_logits": false,
28
- "quantization_config": {
29
- "config_groups": {
30
- "group_0": {
31
- "format": "float-quantized",
32
- "input_activations": {
33
- "actorder": null,
34
- "block_structure": null,
35
- "dynamic": false,
36
- "group_size": null,
37
- "num_bits": 8,
38
- "observer": "minmax",
39
- "observer_kwargs": {},
40
- "strategy": "tensor",
41
- "symmetric": true,
42
- "type": "float"
43
- },
44
- "output_activations": null,
45
- "targets": [
46
- "Linear"
47
- ],
48
- "weights": {
49
- "actorder": null,
50
- "block_structure": null,
51
- "dynamic": false,
52
- "group_size": null,
53
- "num_bits": 8,
54
- "observer": "minmax",
55
- "observer_kwargs": {},
56
- "strategy": "tensor",
57
- "symmetric": true,
58
- "type": "float"
59
- }
60
- }
61
- },
62
- "format": "float-quantized",
63
- "global_compression_ratio": null,
64
- "ignore": [
65
- "model.layers.0.mlp.gate",
66
- "model.layers.1.mlp.gate",
67
- "model.layers.2.mlp.gate",
68
- "model.layers.3.mlp.gate",
69
- "model.layers.4.mlp.gate",
70
- "model.layers.5.mlp.gate",
71
- "model.layers.6.mlp.gate",
72
- "model.layers.7.mlp.gate",
73
- "model.layers.8.mlp.gate",
74
- "model.layers.9.mlp.gate",
75
- "model.layers.10.mlp.gate",
76
- "model.layers.11.mlp.gate",
77
- "model.layers.12.mlp.gate",
78
- "model.layers.13.mlp.gate",
79
- "model.layers.14.mlp.gate",
80
- "model.layers.15.mlp.gate",
81
- "model.layers.16.mlp.gate",
82
- "model.layers.17.mlp.gate",
83
- "model.layers.18.mlp.gate",
84
- "model.layers.19.mlp.gate",
85
- "model.layers.20.mlp.gate",
86
- "model.layers.21.mlp.gate",
87
- "model.layers.22.mlp.gate",
88
- "model.layers.23.mlp.gate",
89
- "model.layers.24.mlp.gate",
90
- "model.layers.25.mlp.gate",
91
- "model.layers.26.mlp.gate",
92
- "model.layers.27.mlp.gate",
93
- "model.layers.28.mlp.gate",
94
- "model.layers.29.mlp.gate",
95
- "model.layers.30.mlp.gate",
96
- "model.layers.31.mlp.gate",
97
- "model.layers.32.mlp.gate",
98
- "model.layers.33.mlp.gate",
99
- "model.layers.34.mlp.gate",
100
- "model.layers.35.mlp.gate",
101
- "model.layers.36.mlp.gate",
102
- "model.layers.37.mlp.gate",
103
- "model.layers.38.mlp.gate",
104
- "model.layers.39.mlp.gate",
105
- "model.layers.40.mlp.gate",
106
- "model.layers.41.mlp.gate",
107
- "model.layers.42.mlp.gate",
108
- "model.layers.43.mlp.gate",
109
- "model.layers.44.mlp.gate",
110
- "model.layers.45.mlp.gate",
111
- "model.layers.46.mlp.gate",
112
- "model.layers.47.mlp.gate",
113
- "lm_head"
114
- ],
115
- "kv_cache_scheme": null,
116
- "quant_method": "compressed-tensors",
117
- "quantization_status": "compressed",
118
- "sparsity_config": {},
119
- "transform_config": {},
120
- "version": "0.12.2"
121
- },
122
- "rms_norm_eps": 1e-06,
123
- "rope_scaling": null,
124
- "rope_theta": 1000000.0,
125
- "router_aux_loss_coef": 0.001,
126
- "sliding_window": null,
127
- "tie_word_embeddings": false,
128
- "transformers_version": "4.56.1",
129
- "use_cache": true,
130
- "use_sliding_window": false,
131
- "vocab_size": 151936
132
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b10c4c23351562e1e34b7953454393621879419b4f68343131f0ddaa2772473
3
+ size 3762
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json CHANGED
@@ -1,13 +1,3 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "temperature": 0.6,
10
- "top_k": 20,
11
- "top_p": 0.95,
12
- "transformers_version": "4.56.1"
13
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4347b1aeed2b2b78bc059920a0b7f5fec71482e1344952b76d7665d638d71f13
3
+ size 214
 
 
 
 
 
 
 
 
 
 
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,31 +1,3 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>"
16
- ],
17
- "eos_token": {
18
- "content": "<|im_end|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- "pad_token": {
25
- "content": "<|endoftext|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- }
31
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
3
+ size 613
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer_config.json CHANGED
@@ -1,239 +1,3 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "151643": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "151644": {
14
- "content": "<|im_start|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "151645": {
22
- "content": "<|im_end|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "151648": {
46
- "content": "<|box_start|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "151649": {
54
- "content": "<|box_end|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "151657": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "151658": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- },
181
- "151665": {
182
- "content": "<tool_response>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": false
188
- },
189
- "151666": {
190
- "content": "</tool_response>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": false
196
- },
197
- "151667": {
198
- "content": "<think>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": false
204
- },
205
- "151668": {
206
- "content": "</think>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": false
212
- }
213
- },
214
- "additional_special_tokens": [
215
- "<|im_start|>",
216
- "<|im_end|>",
217
- "<|object_ref_start|>",
218
- "<|object_ref_end|>",
219
- "<|box_start|>",
220
- "<|box_end|>",
221
- "<|quad_start|>",
222
- "<|quad_end|>",
223
- "<|vision_start|>",
224
- "<|vision_end|>",
225
- "<|vision_pad|>",
226
- "<|image_pad|>",
227
- "<|video_pad|>"
228
- ],
229
- "bos_token": null,
230
- "clean_up_tokenization_spaces": false,
231
- "eos_token": "<|im_end|>",
232
- "errors": "replace",
233
- "extra_special_tokens": {},
234
- "model_max_length": 131072,
235
- "pad_token": "<|endoftext|>",
236
- "split_special_tokens": false,
237
- "tokenizer_class": "Qwen2Tokenizer",
238
- "unk_token": null
239
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:443bfa629eb16387a12edbf92a76f6a6f10b2af3b53d87ba1550adfcf45f7fa0
3
+ size 5404
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vocab.json CHANGED
The diff for this file is too large to render. See raw diff