Hugging Face's logo

Disty0
/
Z-Image-Turbo-SDNQ-int8

Diffusers
Safetensors
ZImagePipeline
sdnq
z_image
8-bit precision
Model card Files
xet
Community
Disty0 commited on
Commit
5aedb00
·
verified ·
1 Parent(s): 253e940

Upload 15 files

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. model_index.json +25 -0
  3. scheduler/scheduler_config.json +18 -0
  4. text_encoder/config.json +119 -0
  5. text_encoder/generation_config.json +13 -0
  6. text_encoder/model.safetensors +3 -0
  7. text_encoder/quantization_config.json +51 -0
  8. tokenizer/merges.txt +0 -0
  9. tokenizer/tokenizer.json +3 -0
  10. tokenizer/tokenizer_config.json +239 -0
  11. tokenizer/vocab.json +0 -0
  12. transformer/config.json +63 -0
  13. transformer/diffusion_pytorch_model.safetensors +3 -0
  14. transformer/quantization_config.json +31 -0
  15. vae/config.json +38 -0
  16. vae/diffusion_pytorch_model.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
model_index.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ZImagePipeline",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "_name_or_path": "Tongyi-MAI/Z-Image-Turbo",
5
+ "scheduler": [
6
+ "diffusers",
7
+ "FlowMatchEulerDiscreteScheduler"
8
+ ],
9
+ "text_encoder": [
10
+ "transformers",
11
+ "Qwen3ForCausalLM"
12
+ ],
13
+ "tokenizer": [
14
+ "transformers",
15
+ "Qwen2Tokenizer"
16
+ ],
17
+ "transformer": [
18
+ "diffusers",
19
+ "ZImageTransformer2DModel"
20
+ ],
21
+ "vae": [
22
+ "diffusers",
23
+ "AutoencoderKL"
24
+ ]
25
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "base_image_seq_len": 256,
5
+ "base_shift": 0.5,
6
+ "invert_sigmas": false,
7
+ "max_image_seq_len": 4096,
8
+ "max_shift": 1.15,
9
+ "num_train_timesteps": 1000,
10
+ "shift": 3.0,
11
+ "shift_terminal": null,
12
+ "stochastic_sampling": false,
13
+ "time_shift_type": "exponential",
14
+ "use_beta_sigmas": false,
15
+ "use_dynamic_shifting": false,
16
+ "use_exponential_sigmas": false,
17
+ "use_karras_sigmas": false
18
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2560,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 9728,
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
+ ],
53
+ "max_position_embeddings": 40960,
54
+ "max_window_layers": 36,
55
+ "model_type": "qwen3",
56
+ "num_attention_heads": 32,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "quantization_config": {
60
+ "add_skip_keys": false,
61
+ "dequantize_fp32": false,
62
+ "group_size": -1,
63
+ "is_integer": true,
64
+ "is_training": false,
65
+ "modules_dtype_dict": {},
66
+ "modules_to_not_convert": [
67
+ ".emb_out",
68
+ "model.norm",
69
+ "multi_modal_projector",
70
+ ".x_embedder",
71
+ ".vid_in",
72
+ "time_text_embed",
73
+ ".condition_embedder",
74
+ ".context_embedder",
75
+ "patch_embedding",
76
+ ".vid_out",
77
+ ".time_embed",
78
+ ".txt_in",
79
+ ".emb_in",
80
+ "patch_embed",
81
+ ".final_layer",
82
+ "patch_emb",
83
+ ".proj_out",
84
+ "lm_head.weight",
85
+ ".norm_out",
86
+ "wte",
87
+ "lm_head",
88
+ ".img_out",
89
+ ".txt_out",
90
+ ".img_in",
91
+ "model.embed_tokens"
92
+ ],
93
+ "non_blocking": false,
94
+ "quant_conv": false,
95
+ "quant_method": "sdnq",
96
+ "quantization_device": null,
97
+ "quantized_matmul_dtype": null,
98
+ "return_device": null,
99
+ "sdnq_version": "0.1.2",
100
+ "svd_rank": 32,
101
+ "svd_steps": 8,
102
+ "use_grad_ckpt": true,
103
+ "use_quantized_matmul": false,
104
+ "use_quantized_matmul_conv": false,
105
+ "use_static_quantization": true,
106
+ "use_stochastic_rounding": false,
107
+ "use_svd": false,
108
+ "weights_dtype": "int8"
109
+ },
110
+ "rms_norm_eps": 1e-06,
111
+ "rope_scaling": null,
112
+ "rope_theta": 1000000,
113
+ "sliding_window": null,
114
+ "tie_word_embeddings": true,
115
+ "transformers_version": "4.57.3",
116
+ "use_cache": true,
117
+ "use_sliding_window": false,
118
+ "vocab_size": 151936
119
+ }
text_encoder/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "4.57.3"
13
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21a5e09e4d05ddb2900dc5c51db5e2bc7bc8b3fa08ba10b372798fba3c594677
3
+ size 4413905040
text_encoder/quantization_config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_skip_keys": false,
3
+ "dequantize_fp32": false,
4
+ "group_size": -1,
5
+ "is_integer": true,
6
+ "is_training": false,
7
+ "modules_dtype_dict": {},
8
+ "modules_to_not_convert": [
9
+ ".emb_out",
10
+ "model.norm",
11
+ "multi_modal_projector",
12
+ ".x_embedder",
13
+ ".vid_in",
14
+ "time_text_embed",
15
+ ".condition_embedder",
16
+ ".context_embedder",
17
+ "patch_embedding",
18
+ ".vid_out",
19
+ ".time_embed",
20
+ ".txt_in",
21
+ ".emb_in",
22
+ "patch_embed",
23
+ ".final_layer",
24
+ "patch_emb",
25
+ ".proj_out",
26
+ "lm_head.weight",
27
+ ".norm_out",
28
+ "wte",
29
+ "lm_head",
30
+ ".img_out",
31
+ ".txt_out",
32
+ ".img_in",
33
+ "model.embed_tokens"
34
+ ],
35
+ "non_blocking": false,
36
+ "quant_conv": false,
37
+ "quant_method": "sdnq",
38
+ "quantization_device": null,
39
+ "quantized_matmul_dtype": null,
40
+ "return_device": null,
41
+ "sdnq_version": "0.1.2",
42
+ "svd_rank": 32,
43
+ "svd_steps": 8,
44
+ "use_grad_ckpt": true,
45
+ "use_quantized_matmul": false,
46
+ "use_quantized_matmul_conv": false,
47
+ "use_static_quantization": true,
48
+ "use_stochastic_rounding": false,
49
+ "use_svd": false,
50
+ "weights_dtype": "int8"
51
+ }
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
transformer/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ZImageTransformer2DModel",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "_name_or_path": "Tongyi-MAI/Z-Image-Turbo",
5
+ "all_f_patch_size": [
6
+ 1
7
+ ],
8
+ "all_patch_size": [
9
+ 2
10
+ ],
11
+ "axes_dims": [
12
+ 32,
13
+ 48,
14
+ 48
15
+ ],
16
+ "axes_lens": [
17
+ 1536,
18
+ 512,
19
+ 512
20
+ ],
21
+ "cap_feat_dim": 2560,
22
+ "dim": 3840,
23
+ "in_channels": 16,
24
+ "n_heads": 30,
25
+ "n_kv_heads": 30,
26
+ "n_layers": 30,
27
+ "n_refiner_layers": 2,
28
+ "norm_eps": 1e-05,
29
+ "qk_norm": true,
30
+ "quantization_config": {
31
+ "add_skip_keys": true,
32
+ "dequantize_fp32": false,
33
+ "group_size": -1,
34
+ "is_integer": true,
35
+ "is_training": false,
36
+ "modules_dtype_dict": {},
37
+ "modules_to_not_convert": [
38
+ "layers.0.adaLN_modulation.0.weight",
39
+ "all_x_embedder",
40
+ "t_embedder",
41
+ "cap_embedder",
42
+ "all_final_layer"
43
+ ],
44
+ "non_blocking": false,
45
+ "quant_conv": false,
46
+ "quant_method": "sdnq",
47
+ "quantization_device": "xpu",
48
+ "quantized_matmul_dtype": null,
49
+ "return_device": "cpu",
50
+ "sdnq_version": "0.1.2",
51
+ "svd_rank": 32,
52
+ "svd_steps": 8,
53
+ "use_grad_ckpt": true,
54
+ "use_quantized_matmul": false,
55
+ "use_quantized_matmul_conv": false,
56
+ "use_static_quantization": true,
57
+ "use_stochastic_rounding": false,
58
+ "use_svd": false,
59
+ "weights_dtype": "int8"
60
+ },
61
+ "rope_theta": 256.0,
62
+ "t_scale": 1000.0
63
+ }
transformer/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc6ce3ed5df327e0ffbbc8f4b82e6fe67a57f42fbab096e6ffa547542954569
3
+ size 6175449256
transformer/quantization_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_skip_keys": false,
3
+ "dequantize_fp32": false,
4
+ "group_size": -1,
5
+ "is_integer": true,
6
+ "is_training": false,
7
+ "modules_dtype_dict": {},
8
+ "modules_to_not_convert": [
9
+ "layers.0.adaLN_modulation.0.weight",
10
+ "all_x_embedder",
11
+ "t_embedder",
12
+ "cap_embedder",
13
+ "all_final_layer"
14
+ ],
15
+ "non_blocking": false,
16
+ "quant_conv": false,
17
+ "quant_method": "sdnq",
18
+ "quantization_device": null,
19
+ "quantized_matmul_dtype": null,
20
+ "return_device": null,
21
+ "sdnq_version": "0.1.2",
22
+ "svd_rank": 32,
23
+ "svd_steps": 8,
24
+ "use_grad_ckpt": true,
25
+ "use_quantized_matmul": false,
26
+ "use_quantized_matmul_conv": false,
27
+ "use_static_quantization": true,
28
+ "use_stochastic_rounding": false,
29
+ "use_svd": false,
30
+ "weights_dtype": "int8"
31
+ }
vae/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "_name_or_path": "/home/disty/.cache/huggingface/hub/models--Tongyi-MAI--Z-Image-Turbo/snapshots/013496ad041be2e9ded1c291c00d8cc4054a6422/vae",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "force_upcast": true,
19
+ "in_channels": 3,
20
+ "latent_channels": 16,
21
+ "latents_mean": null,
22
+ "latents_std": null,
23
+ "layers_per_block": 2,
24
+ "mid_block_add_attention": true,
25
+ "norm_num_groups": 32,
26
+ "out_channels": 3,
27
+ "sample_size": 1024,
28
+ "scaling_factor": 0.3611,
29
+ "shift_factor": 0.1159,
30
+ "up_block_types": [
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D",
33
+ "UpDecoderBlock2D",
34
+ "UpDecoderBlock2D"
35
+ ],
36
+ "use_post_quant_conv": false,
37
+ "use_quant_conv": false
38
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b59a26851551b67ae1fe58d32e76486e1e812def4696a4bea97f16604d40a3
3
+ size 167666902