Hugging Face's logo

OzzyGT
/
Qwen-Image-2512-bnb-4bit-text-encoder

Safetensors
qwen2_5_vl
4-bit precision
bitsandbytes
Model card Files
xet
 Community
OzzyGT HF Staff commited on
Commit
2fd38d0
·
verified ·
1 Parent(s): 81c068f

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +147 -0
  2. generation_config.json +14 -0
  3. model-00001-of-00002.safetensors +3 -0
  4. model-00002-of-00002.safetensors +3 -0
  5. model.safetensors.index.json +0 -0
config.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 128000,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_5_vl",
17
+ "num_attention_heads": 28,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 4,
20
+ "quantization_config": {
21
+ "_load_in_4bit": true,
22
+ "_load_in_8bit": false,
23
+ "bnb_4bit_compute_dtype": "float32",
24
+ "bnb_4bit_quant_storage": "uint8",
25
+ "bnb_4bit_quant_type": "nf4",
26
+ "bnb_4bit_use_double_quant": false,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": true,
32
+ "load_in_8bit": false,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-06,
36
+ "rope_scaling": {
37
+ "mrope_section": [
38
+ 16,
39
+ 24,
40
+ 24
41
+ ],
42
+ "rope_type": "default",
43
+ "type": "default"
44
+ },
45
+ "rope_theta": 1000000.0,
46
+ "sliding_window": 32768,
47
+ "text_config": {
48
+ "_name_or_path": "Qwen/Qwen-Image-2512",
49
+ "architectures": [
50
+ "Qwen2_5_VLForConditionalGeneration"
51
+ ],
52
+ "attention_dropout": 0.0,
53
+ "bos_token_id": 151643,
54
+ "dtype": "bfloat16",
55
+ "eos_token_id": 151645,
56
+ "hidden_act": "silu",
57
+ "hidden_size": 3584,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 18944,
60
+ "layer_types": [
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention",
80
+ "full_attention",
81
+ "full_attention",
82
+ "full_attention",
83
+ "full_attention",
84
+ "full_attention",
85
+ "full_attention",
86
+ "full_attention",
87
+ "full_attention",
88
+ "full_attention"
89
+ ],
90
+ "max_position_embeddings": 128000,
91
+ "max_window_layers": 28,
92
+ "model_type": "qwen2_5_vl_text",
93
+ "num_attention_heads": 28,
94
+ "num_hidden_layers": 28,
95
+ "num_key_value_heads": 4,
96
+ "rms_norm_eps": 1e-06,
97
+ "rope_scaling": {
98
+ "mrope_section": [
99
+ 16,
100
+ 24,
101
+ 24
102
+ ],
103
+ "rope_type": "default",
104
+ "type": "default"
105
+ },
106
+ "rope_theta": 1000000.0,
107
+ "sliding_window": null,
108
+ "use_cache": true,
109
+ "use_sliding_window": false,
110
+ "vision_token_id": 151654,
111
+ "vocab_size": 152064
112
+ },
113
+ "tie_word_embeddings": false,
114
+ "transformers_version": "4.57.3",
115
+ "use_cache": true,
116
+ "use_sliding_window": false,
117
+ "video_token_id": 151656,
118
+ "vision_config": {
119
+ "depth": 32,
120
+ "dtype": "bfloat16",
121
+ "fullatt_block_indexes": [
122
+ 7,
123
+ 15,
124
+ 23,
125
+ 31
126
+ ],
127
+ "hidden_act": "silu",
128
+ "hidden_size": 1280,
129
+ "in_channels": 3,
130
+ "in_chans": 3,
131
+ "initializer_range": 0.02,
132
+ "intermediate_size": 3420,
133
+ "model_type": "qwen2_5_vl",
134
+ "num_heads": 16,
135
+ "out_hidden_size": 3584,
136
+ "patch_size": 14,
137
+ "spatial_merge_size": 2,
138
+ "spatial_patch_size": 14,
139
+ "temporal_patch_size": 2,
140
+ "tokens_per_second": 2,
141
+ "window_size": 112
142
+ },
143
+ "vision_end_token_id": 151653,
144
+ "vision_start_token_id": 151652,
145
+ "vision_token_id": 151654,
146
+ "vocab_size": 152064
147
+ }
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": "4.57.3"
14
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a85f0ecd05a3e32f557ac82c909b25243479a56b7d92789a37c1a8c35db876a
3
+ size 4975533694
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992b628b103caca5b664e7e6f0e24bd001e307f944675977e34d46779a14b48d
3
+ size 1259325330
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff