SceneWorks commited on
Commit
9a52a05
·
verified ·
1 Parent(s): 1dcf289
base/mllm/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 151655,
6
+ "model_type": "qwen3_vl",
7
+ "quantization": {
8
+ "bits": 8,
9
+ "group_size": 32
10
+ },
11
+ "text_config": {
12
+ "attention_bias": false,
13
+ "attention_dropout": 0.0,
14
+ "bos_token_id": 151643,
15
+ "dtype": "bfloat16",
16
+ "eos_token_id": 151645,
17
+ "head_dim": 128,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 4096,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 12288,
22
+ "max_position_embeddings": 262144,
23
+ "model_type": "qwen3_vl_text",
24
+ "num_attention_heads": 32,
25
+ "num_hidden_layers": 36,
26
+ "num_key_value_heads": 8,
27
+ "rms_norm_eps": 1e-6,
28
+ "rope_scaling": {
29
+ "mrope_interleaved": true,
30
+ "mrope_section": [
31
+ 24,
32
+ 20,
33
+ 20
34
+ ],
35
+ "rope_type": "default"
36
+ },
37
+ "rope_theta": 5000000,
38
+ "use_cache": true,
39
+ "vocab_size": 151936
40
+ },
41
+ "tie_word_embeddings": false,
42
+ "transformers_version": "4.57.0.dev0",
43
+ "video_token_id": 151656,
44
+ "vision_config": {
45
+ "deepstack_visual_indexes": [
46
+ 8,
47
+ 16,
48
+ 24
49
+ ],
50
+ "depth": 27,
51
+ "hidden_act": "gelu_pytorch_tanh",
52
+ "hidden_size": 1152,
53
+ "in_channels": 3,
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 4304,
56
+ "model_type": "qwen3_vl",
57
+ "num_heads": 16,
58
+ "num_position_embeddings": 2304,
59
+ "out_hidden_size": 4096,
60
+ "patch_size": 16,
61
+ "spatial_merge_size": 2,
62
+ "temporal_patch_size": 2
63
+ },
64
+ "vision_end_token_id": 151653,
65
+ "vision_start_token_id": 151652
66
+ }
base/mllm/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e331c73e026668dc73d156795fffc63f2848c2ab4b1bbba1fe3d5113fe2afe22
3
+ size 11456858687
base/mllm/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
base/transformer/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "BooguImageTransformer2DModel",
3
+ "_diffusers_version": "0.35.2",
4
+ "axes_dim_rope": [
5
+ 40,
6
+ 40,
7
+ 40
8
+ ],
9
+ "axes_lens": [
10
+ 2048,
11
+ 1664,
12
+ 1664
13
+ ],
14
+ "ffn_dim_multiplier": null,
15
+ "hidden_size": 3360,
16
+ "in_channels": 16,
17
+ "instruction_feature_configs": {
18
+ "instruction_feat_dim": 4096,
19
+ "num_instruction_feature_layers": 1,
20
+ "reduce_type": "mean"
21
+ },
22
+ "multiple_of": 256,
23
+ "norm_eps": 0.00001,
24
+ "num_attention_heads": 28,
25
+ "num_double_stream_layers": 8,
26
+ "num_kv_heads": 7,
27
+ "num_layers": 40,
28
+ "num_refiner_layers": 2,
29
+ "out_channels": null,
30
+ "patch_size": 2,
31
+ "prompt_tuning_configs": {
32
+ "ffn_dim_multiplier": null,
33
+ "hidden_size": 4096,
34
+ "multiple_of": 256,
35
+ "norm_eps": 0.00001,
36
+ "num_attention_heads": 32,
37
+ "num_kv_heads": 8,
38
+ "num_layers": 0,
39
+ "num_trainable_prompt_tokens": 0,
40
+ "use_causal_mask": true,
41
+ "use_prompt_tuning": false
42
+ },
43
+ "quantization": {
44
+ "bits": 8,
45
+ "group_size": 32
46
+ },
47
+ "timestep_scale": 1000.0
48
+ }
base/transformer/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e25c2f626326124ed4f27d36d34eb6477e329749d55cc19e1c2896666b997797
3
+ size 11581034057
base/vae/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.35.2",
4
+ "_name_or_path": "/share_2/luoxin/modelscope/hub/models/FLUX.1-dev",
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
+ }
base/vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c717328c8ad41faab2ccfd52ae17332505c6833cf176aad56e7b58f2c4d4c94
3
+ size 335306212