Hugging Face's logo

Meatfucker
/
Qwen-Image-bnb-nf4

Text-to-Image
Diffusers
Safetensors
QwenImagePipeline
Model card Files
xet
Community
Meatfucker commited on
Commit
6601bb7
·
verified ·
1 Parent(s): dbc8a4f

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. model_index.json +25 -0
  2. scheduler/scheduler_config.json +18 -0
  3. text_encoder/config.json +181 -0
  4. text_encoder/generation_config.json +14 -0
  5. text_encoder/model-00001-of-00002.safetensors +3 -0
  6. text_encoder/model-00002-of-00002.safetensors +3 -0
  7. text_encoder/model.safetensors.index.json +0 -0
  8. tokenizer/added_tokens.json +24 -0
  9. tokenizer/chat_template.jinja +54 -0
  10. tokenizer/merges.txt +0 -0
  11. tokenizer/special_tokens_map.json +31 -0
  12. tokenizer/tokenizer_config.json +207 -0
  13. tokenizer/vocab.json +0 -0
  14. transformer/config.json +65 -0
  15. transformer/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  16. transformer/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  17. transformer/diffusion_pytorch_model.safetensors.index.json +0 -0
  18. vae/config.json +57 -0
  19. vae/diffusion_pytorch_model.safetensors +3 -0
model_index.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "QwenImagePipeline",
3
+ "_diffusers_version": "0.35.1",
4
+ "_name_or_path": "Qwen/Qwen-Image",
5
+ "scheduler": [
6
+ "diffusers",
7
+ "FlowMatchEulerDiscreteScheduler"
8
+ ],
9
+ "text_encoder": [
10
+ "transformers",
11
+ "Qwen2_5_VLForConditionalGeneration"
12
+ ],
13
+ "tokenizer": [
14
+ "transformers",
15
+ "Qwen2Tokenizer"
16
+ ],
17
+ "transformer": [
18
+ "diffusers",
19
+ "QwenImageTransformer2DModel"
20
+ ],
21
+ "vae": [
22
+ "diffusers",
23
+ "AutoencoderKLQwenImage"
24
+ ]
25
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
3
+ "_diffusers_version": "0.35.1",
4
+ "base_image_seq_len": 256,
5
+ "base_shift": 0.5,
6
+ "invert_sigmas": false,
7
+ "max_image_seq_len": 8192,
8
+ "max_shift": 0.9,
9
+ "num_train_timesteps": 1000,
10
+ "shift": 1.0,
11
+ "shift_terminal": 0.02,
12
+ "stochastic_sampling": false,
13
+ "time_shift_type": "exponential",
14
+ "use_beta_sigmas": false,
15
+ "use_dynamic_shifting": true,
16
+ "use_exponential_sigmas": false,
17
+ "use_karras_sigmas": false
18
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "quantization_config": {
20
+ "_load_in_4bit": true,
21
+ "_load_in_8bit": false,
22
+ "bnb_4bit_compute_dtype": "bfloat16",
23
+ "bnb_4bit_quant_storage": "uint8",
24
+ "bnb_4bit_quant_type": "nf4",
25
+ "bnb_4bit_use_double_quant": true,
26
+ "llm_int8_enable_fp32_cpu_offload": false,
27
+ "llm_int8_has_fp16_weight": false,
28
+ "llm_int8_skip_modules": [
29
+ "transformer_blocks.0.img_mod.1",
30
+ "transformer_blocks.0.attn.to_q",
31
+ "transformer_blocks.0.attn.to_k",
32
+ "transformer_blocks.0.attn.to_v",
33
+ "transformer_blocks.0.attn.add_k_proj",
34
+ "transformer_blocks.0.attn.add_v_proj",
35
+ "transformer_blocks.0.attn.add_q_proj",
36
+ "transformer_blocks.0.attn.to_out.0",
37
+ "transformer_blocks.0.attn.to_add_out",
38
+ "transformer_blocks.0.img_mlp.net.0.proj",
39
+ "transformer_blocks.0.img_mlp.net.2",
40
+ "transformer_blocks.0.txt_mod.1",
41
+ "transformer_blocks.0.txt_mlp.net.0.proj",
42
+ "transformer_blocks.0.txt_mlp.net.2",
43
+ "transformer_blocks.59.img_mod.1",
44
+ "transformer_blocks.59.attn.to_q",
45
+ "transformer_blocks.59.attn.to_k",
46
+ "transformer_blocks.59.attn.to_v",
47
+ "transformer_blocks.59.attn.add_k_proj",
48
+ "transformer_blocks.59.attn.add_v_proj",
49
+ "transformer_blocks.59.attn.add_q_proj",
50
+ "transformer_blocks.59.attn.to_out.0",
51
+ "transformer_blocks.59.attn.to_add_out",
52
+ "transformer_blocks.59.img_mlp.net.0.proj",
53
+ "transformer_blocks.59.img_mlp.net.2",
54
+ "transformer_blocks.59.txt_mod.1",
55
+ "transformer_blocks.59.txt_mlp.net.0.proj",
56
+ "transformer_blocks.59.txt_mlp.net.2",
57
+ "norm_out.linear",
58
+ "proj_out"
59
+ ],
60
+ "llm_int8_threshold": 6.0,
61
+ "load_in_4bit": true,
62
+ "load_in_8bit": false,
63
+ "quant_method": "bitsandbytes"
64
+ },
65
+ "rms_norm_eps": 1e-06,
66
+ "rope_scaling": {
67
+ "mrope_section": [
68
+ 16,
69
+ 24,
70
+ 24
71
+ ],
72
+ "rope_type": "default",
73
+ "type": "default"
74
+ },
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": 32768,
77
+ "text_config": {
78
+ "architectures": [
79
+ "Qwen2_5_VLForConditionalGeneration"
80
+ ],
81
+ "attention_dropout": 0.0,
82
+ "bos_token_id": 151643,
83
+ "eos_token_id": 151645,
84
+ "hidden_act": "silu",
85
+ "hidden_size": 3584,
86
+ "image_token_id": null,
87
+ "initializer_range": 0.02,
88
+ "intermediate_size": 18944,
89
+ "layer_types": [
90
+ "full_attention",
91
+ "full_attention",
92
+ "full_attention",
93
+ "full_attention",
94
+ "full_attention",
95
+ "full_attention",
96
+ "full_attention",
97
+ "full_attention",
98
+ "full_attention",
99
+ "full_attention",
100
+ "full_attention",
101
+ "full_attention",
102
+ "full_attention",
103
+ "full_attention",
104
+ "full_attention",
105
+ "full_attention",
106
+ "full_attention",
107
+ "full_attention",
108
+ "full_attention",
109
+ "full_attention",
110
+ "full_attention",
111
+ "full_attention",
112
+ "full_attention",
113
+ "full_attention",
114
+ "full_attention",
115
+ "full_attention",
116
+ "full_attention",
117
+ "full_attention"
118
+ ],
119
+ "max_position_embeddings": 128000,
120
+ "max_window_layers": 28,
121
+ "model_type": "qwen2_5_vl_text",
122
+ "num_attention_heads": 28,
123
+ "num_hidden_layers": 28,
124
+ "num_key_value_heads": 4,
125
+ "rms_norm_eps": 1e-06,
126
+ "rope_scaling": {
127
+ "mrope_section": [
128
+ 16,
129
+ 24,
130
+ 24
131
+ ],
132
+ "rope_type": "default",
133
+ "type": "default"
134
+ },
135
+ "rope_theta": 1000000.0,
136
+ "sliding_window": null,
137
+ "torch_dtype": "bfloat16",
138
+ "use_cache": true,
139
+ "use_sliding_window": false,
140
+ "video_token_id": null,
141
+ "vision_end_token_id": 151653,
142
+ "vision_start_token_id": 151652,
143
+ "vision_token_id": 151654,
144
+ "vocab_size": 152064
145
+ },
146
+ "tie_word_embeddings": false,
147
+ "torch_dtype": "bfloat16",
148
+ "transformers_version": "4.55.4",
149
+ "use_cache": true,
150
+ "use_sliding_window": false,
151
+ "video_token_id": 151656,
152
+ "vision_config": {
153
+ "depth": 32,
154
+ "fullatt_block_indexes": [
155
+ 7,
156
+ 15,
157
+ 23,
158
+ 31
159
+ ],
160
+ "hidden_act": "silu",
161
+ "hidden_size": 1280,
162
+ "in_channels": 3,
163
+ "in_chans": 3,
164
+ "initializer_range": 0.02,
165
+ "intermediate_size": 3420,
166
+ "model_type": "qwen2_5_vl",
167
+ "num_heads": 16,
168
+ "out_hidden_size": 3584,
169
+ "patch_size": 14,
170
+ "spatial_merge_size": 2,
171
+ "spatial_patch_size": 14,
172
+ "temporal_patch_size": 2,
173
+ "tokens_per_second": 2,
174
+ "torch_dtype": "bfloat16",
175
+ "window_size": 112
176
+ },
177
+ "vision_end_token_id": 151653,
178
+ "vision_start_token_id": 151652,
179
+ "vision_token_id": 151654,
180
+ "vocab_size": 152064
181
+ }
text_encoder/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.1,
11
+ "top_k": 1,
12
+ "top_p": 0.001,
13
+ "transformers_version": "4.55.4"
14
+ }
text_encoder/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1905aae08b7a148c6f2a69939fe196c314f7a75652934e7b85fe222976a28663
3
+ size 4809612598
text_encoder/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b727105e5dbd38583aee6a600cad89d2c911ed6592b728702fd4bb60f108704
3
+ size 281149198
text_encoder/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
transformer/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "QwenImageTransformer2DModel",
3
+ "_diffusers_version": "0.35.1",
4
+ "_name_or_path": "Qwen/Qwen-Image",
5
+ "attention_head_dim": 128,
6
+ "axes_dims_rope": [
7
+ 16,
8
+ 56,
9
+ 56
10
+ ],
11
+ "guidance_embeds": false,
12
+ "in_channels": 64,
13
+ "joint_attention_dim": 3584,
14
+ "num_attention_heads": 24,
15
+ "num_layers": 60,
16
+ "out_channels": 16,
17
+ "patch_size": 2,
18
+ "pooled_projection_dim": 768,
19
+ "quantization_config": {
20
+ "_load_in_4bit": true,
21
+ "_load_in_8bit": false,
22
+ "bnb_4bit_compute_dtype": "bfloat16",
23
+ "bnb_4bit_quant_storage": "uint8",
24
+ "bnb_4bit_quant_type": "nf4",
25
+ "bnb_4bit_use_double_quant": false,
26
+ "llm_int8_enable_fp32_cpu_offload": false,
27
+ "llm_int8_has_fp16_weight": false,
28
+ "llm_int8_skip_modules": [
29
+ "transformer_blocks.0.img_mod.1",
30
+ "transformer_blocks.0.attn.to_q",
31
+ "transformer_blocks.0.attn.to_k",
32
+ "transformer_blocks.0.attn.to_v",
33
+ "transformer_blocks.0.attn.add_k_proj",
34
+ "transformer_blocks.0.attn.add_v_proj",
35
+ "transformer_blocks.0.attn.add_q_proj",
36
+ "transformer_blocks.0.attn.to_out.0",
37
+ "transformer_blocks.0.attn.to_add_out",
38
+ "transformer_blocks.0.img_mlp.net.0.proj",
39
+ "transformer_blocks.0.img_mlp.net.2",
40
+ "transformer_blocks.0.txt_mod.1",
41
+ "transformer_blocks.0.txt_mlp.net.0.proj",
42
+ "transformer_blocks.0.txt_mlp.net.2",
43
+ "transformer_blocks.59.img_mod.1",
44
+ "transformer_blocks.59.attn.to_q",
45
+ "transformer_blocks.59.attn.to_k",
46
+ "transformer_blocks.59.attn.to_v",
47
+ "transformer_blocks.59.attn.add_k_proj",
48
+ "transformer_blocks.59.attn.add_v_proj",
49
+ "transformer_blocks.59.attn.add_q_proj",
50
+ "transformer_blocks.59.attn.to_out.0",
51
+ "transformer_blocks.59.attn.to_add_out",
52
+ "transformer_blocks.59.img_mlp.net.0.proj",
53
+ "transformer_blocks.59.img_mlp.net.2",
54
+ "transformer_blocks.59.txt_mod.1",
55
+ "transformer_blocks.59.txt_mlp.net.0.proj",
56
+ "transformer_blocks.59.txt_mlp.net.2",
57
+ "norm_out.linear",
58
+ "proj_out"
59
+ ],
60
+ "llm_int8_threshold": 6.0,
61
+ "load_in_4bit": true,
62
+ "load_in_8bit": false,
63
+ "quant_method": "bitsandbytes"
64
+ }
65
+ }
transformer/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d891ef25bdf7fdbf064295a0e1f333c9951d23e0adf9a860dfbba2f680979d83
3
+ size 9991041702
transformer/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d392f3edec5e07ed18be78c5750252d230bb838a1660cb6d95e3c59f3eb0f6e
3
+ size 2513903499
transformer/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
vae/config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLQwenImage",
3
+ "_diffusers_version": "0.35.1",
4
+ "_name_or_path": "/mnt/1000gb/ml/huggingface/hub/models--Qwen--Qwen-Image/snapshots/75e0b4be04f60ec59a75f475837eced720f823b6/vae",
5
+ "attn_scales": [],
6
+ "base_dim": 96,
7
+ "dim_mult": [
8
+ 1,
9
+ 2,
10
+ 4,
11
+ 4
12
+ ],
13
+ "dropout": 0.0,
14
+ "latents_mean": [
15
+ -0.7571,
16
+ -0.7089,
17
+ -0.9113,
18
+ 0.1075,
19
+ -0.1745,
20
+ 0.9653,
21
+ -0.1517,
22
+ 1.5508,
23
+ 0.4134,
24
+ -0.0715,
25
+ 0.5517,
26
+ -0.3632,
27
+ -0.1922,
28
+ -0.9497,
29
+ 0.2503,
30
+ -0.2921
31
+ ],
32
+ "latents_std": [
33
+ 2.8184,
34
+ 1.4541,
35
+ 2.3275,
36
+ 2.6558,
37
+ 1.2196,
38
+ 1.7708,
39
+ 2.6052,
40
+ 2.0743,
41
+ 3.2687,
42
+ 2.1526,
43
+ 2.8652,
44
+ 1.5579,
45
+ 1.6382,
46
+ 1.1253,
47
+ 2.8251,
48
+ 1.916
49
+ ],
50
+ "num_res_blocks": 2,
51
+ "temperal_downsample": [
52
+ false,
53
+ true,
54
+ true
55
+ ],
56
+ "z_dim": 16
57
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8bc8b758c649abef9ea407b95408389a3b2f610d0d10fcb054fe171d0a8344
3
+ size 253806966