Hugging Face's logo

twodgirl
/
omnigen2-nf4-bfloat16-diffusers

Diffusers
Safetensors
OmniGen2Pipeline
Model card Files
twodgirl commited on
Commit
5b2ec39
·
verified ·
1 Parent(s): 4b800b1

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. mllm/.gitattributes +36 -0
  2. mllm/.ipynb_checkpoints/config-checkpoint.json +86 -0
  3. mllm/.ipynb_checkpoints/generation_config-checkpoint.json +15 -0
  4. mllm/config.json +86 -0
  5. mllm/generation_config.json +15 -0
  6. mllm/model.safetensors +3 -0
mllm/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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.json filter=lfs diff=lfs merge=lfs -text
mllm/.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "eos_token_id": 151645,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 2048,
9
+ "image_token_id": 151655,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 128000,
13
+ "max_window_layers": 70,
14
+ "model_type": "qwen2_5_vl",
15
+ "num_attention_heads": 16,
16
+ "num_hidden_layers": 36,
17
+ "num_key_value_heads": 2,
18
+ "pad_token_id": 151654,
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
+ "lm_head",
30
+ "multi_modal_projector",
31
+ "merger",
32
+ "modality_projection"
33
+ ],
34
+ "llm_int8_threshold": 6.0,
35
+ "load_in_4bit": true,
36
+ "load_in_8bit": false,
37
+ "quant_method": "bitsandbytes"
38
+ },
39
+ "rms_norm_eps": 1e-06,
40
+ "rope_scaling": {
41
+ "mrope_section": [
42
+ 16,
43
+ 24,
44
+ 24
45
+ ],
46
+ "rope_type": "default",
47
+ "type": "default"
48
+ },
49
+ "rope_theta": 1000000.0,
50
+ "sliding_window": 32768,
51
+ "tie_word_embeddings": true,
52
+ "torch_dtype": "bfloat16",
53
+ "transformers_version": "4.51.3",
54
+ "unsloth_fixed": true,
55
+ "use_cache": true,
56
+ "use_sliding_window": false,
57
+ "video_token_id": 151656,
58
+ "vision_config": {
59
+ "depth": 32,
60
+ "fullatt_block_indexes": [
61
+ 7,
62
+ 15,
63
+ 23,
64
+ 31
65
+ ],
66
+ "hidden_act": "silu",
67
+ "hidden_size": 1280,
68
+ "in_channels": 3,
69
+ "in_chans": 3,
70
+ "intermediate_size": 3420,
71
+ "model_type": "qwen2_5_vl",
72
+ "num_heads": 16,
73
+ "out_hidden_size": 2048,
74
+ "patch_size": 14,
75
+ "spatial_merge_size": 2,
76
+ "spatial_patch_size": 14,
77
+ "temporal_patch_size": 2,
78
+ "tokens_per_second": 2,
79
+ "torch_dtype": "bfloat16",
80
+ "window_size": 112
81
+ },
82
+ "vision_end_token_id": 151653,
83
+ "vision_start_token_id": 151652,
84
+ "vision_token_id": 151654,
85
+ "vocab_size": 151936
86
+ }
mllm/.ipynb_checkpoints/generation_config-checkpoint.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation": "flash_attention_2",
3
+ "bos_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "pad_token_id": 151643,
10
+ "repetition_penalty": 1.05,
11
+ "temperature": 0.1,
12
+ "top_k": 1,
13
+ "top_p": 0.001,
14
+ "transformers_version": "4.51.3"
15
+ }
mllm/config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "eos_token_id": 151645,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 2048,
9
+ "image_token_id": 151655,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 128000,
13
+ "max_window_layers": 70,
14
+ "model_type": "qwen2_5_vl",
15
+ "num_attention_heads": 16,
16
+ "num_hidden_layers": 36,
17
+ "num_key_value_heads": 2,
18
+ "pad_token_id": 151654,
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
+ "lm_head",
30
+ "multi_modal_projector",
31
+ "merger",
32
+ "modality_projection"
33
+ ],
34
+ "llm_int8_threshold": 6.0,
35
+ "load_in_4bit": true,
36
+ "load_in_8bit": false,
37
+ "quant_method": "bitsandbytes"
38
+ },
39
+ "rms_norm_eps": 1e-06,
40
+ "rope_scaling": {
41
+ "mrope_section": [
42
+ 16,
43
+ 24,
44
+ 24
45
+ ],
46
+ "rope_type": "default",
47
+ "type": "default"
48
+ },
49
+ "rope_theta": 1000000.0,
50
+ "sliding_window": 32768,
51
+ "tie_word_embeddings": true,
52
+ "torch_dtype": "bfloat16",
53
+ "transformers_version": "4.51.3",
54
+ "unsloth_fixed": true,
55
+ "use_cache": true,
56
+ "use_sliding_window": false,
57
+ "video_token_id": 151656,
58
+ "vision_config": {
59
+ "depth": 32,
60
+ "fullatt_block_indexes": [
61
+ 7,
62
+ 15,
63
+ 23,
64
+ 31
65
+ ],
66
+ "hidden_act": "silu",
67
+ "hidden_size": 1280,
68
+ "in_channels": 3,
69
+ "in_chans": 3,
70
+ "intermediate_size": 3420,
71
+ "model_type": "qwen2_5_vl",
72
+ "num_heads": 16,
73
+ "out_hidden_size": 2048,
74
+ "patch_size": 14,
75
+ "spatial_merge_size": 2,
76
+ "spatial_patch_size": 14,
77
+ "temporal_patch_size": 2,
78
+ "tokens_per_second": 2,
79
+ "torch_dtype": "bfloat16",
80
+ "window_size": 112
81
+ },
82
+ "vision_end_token_id": 151653,
83
+ "vision_start_token_id": 151652,
84
+ "vision_token_id": 151654,
85
+ "vocab_size": 151936
86
+ }
mllm/generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation": "flash_attention_2",
3
+ "bos_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "pad_token_id": 151643,
10
+ "repetition_penalty": 1.05,
11
+ "temperature": 0.1,
12
+ "top_k": 1,
13
+ "top_p": 0.001,
14
+ "transformers_version": "4.51.3"
15
+ }
mllm/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6959136e8c58305b856340f8fcac76d459be0a36119567cd2c434ce2c04f573b
3
+ size 2457382029