Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- mmflow-libero/libero-s1/30000/adapters/transformer/adapter_model.safetensors +3 -0
- mmflow-libero/libero-s1/30000/assets/norm_stats.json +154 -0
- mmflow-libero/libero-s1/30000/config.json +17 -0
- mmflow-libero/libero-s1/30000/img_vae/config.json +16 -0
- mmflow-libero/libero-s1/30000/img_vae/model.safetensors +3 -0
- mmflow-libero/libero-s1/30000/metadata.pt +3 -0
- mmflow-libero/libero-s1/30000/optimizer.pt +3 -0
- mmflow-libero/libero-s1/30000/scheduler.pt +3 -0
- mmflow-libero/libero-s1/30000/transformer/config.json +29 -0
- mmflow-libero/libero-s1/30000/transformer/model.safetensors +3 -0
- mmflow-libero/libero-s1/30000/vlm/config.json +22 -0
- mmflow-libero/libero-s1/30000/vlm/inner_model/added_tokens.json +28 -0
- mmflow-libero/libero-s1/30000/vlm/inner_model/chat_template.jinja +120 -0
- mmflow-libero/libero-s1/30000/vlm/inner_model/config.json +80 -0
- mmflow-libero/libero-s1/30000/vlm/inner_model/generation_config.json +13 -0
- mmflow-libero/libero-s1/30000/vlm/inner_model/merges.txt +0 -0
- mmflow-libero/libero-s1/30000/vlm/inner_model/model.safetensors +3 -0
- mmflow-libero/libero-s1/30000/vlm/inner_model/preprocessor_config.json +39 -0
- mmflow-libero/libero-s1/30000/vlm/inner_model/special_tokens_map.json +31 -0
- mmflow-libero/libero-s1/30000/vlm/inner_model/tokenizer.json +3 -0
- mmflow-libero/libero-s1/30000/vlm/inner_model/tokenizer_config.json +240 -0
- mmflow-libero/libero-s1/30000/vlm/inner_model/video_preprocessor_config.json +41 -0
- mmflow-libero/libero-s1/30000/vlm/inner_model/vocab.json +0 -0
- mmflow-libero/libero-s1/30000/vlm/model.safetensors +3 -0
- mmflow-libero/libero-s1/trainable_parameters.txt +910 -0
- mmflow-libero/libero-s1/wandb_id.txt +1 -0
.gitattributes
CHANGED
|
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
pretrain-b-s1/vlm/inner_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
30000/vlm/inner_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
pretrain-b-s1/vlm/inner_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
30000/vlm/inner_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
mmflow-libero/libero-s1/30000/vlm/inner_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
mmflow-libero/libero-s1/30000/adapters/transformer/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df8c7e99d2a4db785df1ab4e6448b0e6f001fbbad08c3ddae438a933591ffcd4
|
| 3 |
+
size 88553624
|
mmflow-libero/libero-s1/30000/assets/norm_stats.json
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"norm_stats": {
|
| 3 |
+
"state": {
|
| 4 |
+
"count": 273408,
|
| 5 |
+
"mean": [
|
| 6 |
+
-0.046515832679548515,
|
| 7 |
+
0.03437810533502129,
|
| 8 |
+
0.7644975640800562,
|
| 9 |
+
2.9721761982092696,
|
| 10 |
+
-0.2203380713302098,
|
| 11 |
+
-0.12565075592155314,
|
| 12 |
+
0.026918238021907737,
|
| 13 |
+
-0.02719479107231683,
|
| 14 |
+
0.0,
|
| 15 |
+
0.0,
|
| 16 |
+
0.0,
|
| 17 |
+
0.0,
|
| 18 |
+
0.0,
|
| 19 |
+
0.0,
|
| 20 |
+
0.0,
|
| 21 |
+
0.0
|
| 22 |
+
],
|
| 23 |
+
"std": [
|
| 24 |
+
0.1049430405120553,
|
| 25 |
+
0.15176749532203646,
|
| 26 |
+
0.37853701762601316,
|
| 27 |
+
0.34430596099033595,
|
| 28 |
+
0.9069933264633429,
|
| 29 |
+
0.32538961158764335,
|
| 30 |
+
0.014174073074704035,
|
| 31 |
+
0.01405701171059929,
|
| 32 |
+
0.0,
|
| 33 |
+
0.0,
|
| 34 |
+
0.0,
|
| 35 |
+
0.0,
|
| 36 |
+
0.0,
|
| 37 |
+
0.0,
|
| 38 |
+
0.0,
|
| 39 |
+
0.0
|
| 40 |
+
],
|
| 41 |
+
"q01": [
|
| 42 |
+
-0.39929718182235957,
|
| 43 |
+
-0.2688781352341175,
|
| 44 |
+
0.0380015922319144,
|
| 45 |
+
1.5076640663146972,
|
| 46 |
+
-2.7231650549173354,
|
| 47 |
+
-1.082290536224842,
|
| 48 |
+
0.0017220906309667046,
|
| 49 |
+
-0.04006594421766931,
|
| 50 |
+
0.0,
|
| 51 |
+
0.0,
|
| 52 |
+
0.0,
|
| 53 |
+
0.0,
|
| 54 |
+
0.0,
|
| 55 |
+
0.0,
|
| 56 |
+
0.0,
|
| 57 |
+
0.0
|
| 58 |
+
],
|
| 59 |
+
"q99": [
|
| 60 |
+
0.13511216131597759,
|
| 61 |
+
0.3353764298558235,
|
| 62 |
+
1.2689219574783928,
|
| 63 |
+
3.2748465917110443,
|
| 64 |
+
2.40471659219265,
|
| 65 |
+
0.5968299900889398,
|
| 66 |
+
0.040285861361655406,
|
| 67 |
+
-0.0018051995920250197,
|
| 68 |
+
0.0,
|
| 69 |
+
0.0,
|
| 70 |
+
0.0,
|
| 71 |
+
0.0,
|
| 72 |
+
0.0,
|
| 73 |
+
0.0,
|
| 74 |
+
0.0,
|
| 75 |
+
0.0
|
| 76 |
+
]
|
| 77 |
+
},
|
| 78 |
+
"actions": {
|
| 79 |
+
"count": 273408,
|
| 80 |
+
"mean": [
|
| 81 |
+
0.06270760811223519,
|
| 82 |
+
0.0868575278292881,
|
| 83 |
+
-0.09040560347310612,
|
| 84 |
+
0.0005443644769182812,
|
| 85 |
+
0.00564395800958412,
|
| 86 |
+
-0.005221108818768562,
|
| 87 |
+
0.0,
|
| 88 |
+
0.5248822272940075,
|
| 89 |
+
0.0,
|
| 90 |
+
0.0,
|
| 91 |
+
0.0,
|
| 92 |
+
0.0,
|
| 93 |
+
0.0,
|
| 94 |
+
0.0,
|
| 95 |
+
0.0,
|
| 96 |
+
0.0
|
| 97 |
+
],
|
| 98 |
+
"std": [
|
| 99 |
+
0.33547515422916885,
|
| 100 |
+
0.37848309424500604,
|
| 101 |
+
0.44467916095569604,
|
| 102 |
+
0.039240949042962214,
|
| 103 |
+
0.06338541435693439,
|
| 104 |
+
0.07797358906933648,
|
| 105 |
+
0.0,
|
| 106 |
+
0.4993804909734554,
|
| 107 |
+
0.0,
|
| 108 |
+
0.0,
|
| 109 |
+
0.0,
|
| 110 |
+
0.0,
|
| 111 |
+
0.0,
|
| 112 |
+
0.0,
|
| 113 |
+
0.0,
|
| 114 |
+
0.0
|
| 115 |
+
],
|
| 116 |
+
"q01": [
|
| 117 |
+
-0.7050000000000001,
|
| 118 |
+
-0.8015625,
|
| 119 |
+
-0.9375,
|
| 120 |
+
-0.11486197002232074,
|
| 121 |
+
-0.16425,
|
| 122 |
+
-0.22419750577211378,
|
| 123 |
+
0.0,
|
| 124 |
+
0.0,
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
0.0,
|
| 129 |
+
0.0,
|
| 130 |
+
0.0,
|
| 131 |
+
0.0,
|
| 132 |
+
0.0
|
| 133 |
+
],
|
| 134 |
+
"q99": [
|
| 135 |
+
0.9365625,
|
| 136 |
+
0.8671875,
|
| 137 |
+
0.9365625,
|
| 138 |
+
0.13070946447551252,
|
| 139 |
+
0.19274999999999998,
|
| 140 |
+
0.33490499961376197,
|
| 141 |
+
0.0,
|
| 142 |
+
0.9995,
|
| 143 |
+
0.0,
|
| 144 |
+
0.0,
|
| 145 |
+
0.0,
|
| 146 |
+
0.0,
|
| 147 |
+
0.0,
|
| 148 |
+
0.0,
|
| 149 |
+
0.0,
|
| 150 |
+
0.0
|
| 151 |
+
]
|
| 152 |
+
}
|
| 153 |
+
}
|
| 154 |
+
}
|
mmflow-libero/libero-s1/30000/config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "QWenVLA",
|
| 3 |
+
"_diffusers_version": "0.35.1",
|
| 4 |
+
"_load_submodules": true,
|
| 5 |
+
"action_dim": 16,
|
| 6 |
+
"action_horizon": 30,
|
| 7 |
+
"dit_variant": "mmflow-base",
|
| 8 |
+
"img_vae_variant": "qwen-image",
|
| 9 |
+
"max_views": 3,
|
| 10 |
+
"patch_size": 2,
|
| 11 |
+
"strength": 1.0,
|
| 12 |
+
"use_goal_image": true,
|
| 13 |
+
"use_primary_goal_image_only": true,
|
| 14 |
+
"vlm_load_in_4bit": true,
|
| 15 |
+
"vlm_load_in_8bit": false,
|
| 16 |
+
"vlm_variant": "qwen3-vl-4b"
|
| 17 |
+
}
|
mmflow-libero/libero-s1/30000/img_vae/config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HuggingFaceVAE"
|
| 4 |
+
],
|
| 5 |
+
"device_map": "auto",
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"freeze": true,
|
| 8 |
+
"latent_channels": 16,
|
| 9 |
+
"model_dtype": "bfloat16",
|
| 10 |
+
"model_type": "vision_vae",
|
| 11 |
+
"name": "Qwen/Qwen-Image",
|
| 12 |
+
"patch_size": 8,
|
| 13 |
+
"transformers_version": "4.57.0",
|
| 14 |
+
"trust_remote_code": true,
|
| 15 |
+
"vae_type": "autoencoder_kl"
|
| 16 |
+
}
|
mmflow-libero/libero-s1/30000/img_vae/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9646c3092eed46c221c1e11c3e6c58e4f8860f93f467f95b6f64fc1c4629524
|
| 3 |
+
size 253807742
|
mmflow-libero/libero-s1/30000/metadata.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d70d4e8d01e7af2f678d643b201eab488c978caa963544c1a4f53b027cd7c24
|
| 3 |
+
size 3699
|
mmflow-libero/libero-s1/30000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06cafafd66948a0496c2e41dda78eac9ebd490a080d8310c449f8e305285006e
|
| 3 |
+
size 175280599
|
mmflow-libero/libero-s1/30000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a78ceaa66f62910fbe9ac23e14b4075d560f243758249984b2212d7031cca631
|
| 3 |
+
size 1401
|
mmflow-libero/libero-s1/30000/transformer/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"action_dim": 16,
|
| 3 |
+
"action_horizon": 30,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"MMFlowTransformer"
|
| 6 |
+
],
|
| 7 |
+
"condition_dim": 768,
|
| 8 |
+
"dim_head": 64,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embed_dim": 768,
|
| 11 |
+
"ff_kwargs": {
|
| 12 |
+
"hidden_features": 3072
|
| 13 |
+
},
|
| 14 |
+
"img_vae_patch_size": 8,
|
| 15 |
+
"in_channels": 16,
|
| 16 |
+
"max_views": 3,
|
| 17 |
+
"model_type": "mmflow_transformer",
|
| 18 |
+
"name": "mmflow-base",
|
| 19 |
+
"num_blocks": 28,
|
| 20 |
+
"num_heads": 12,
|
| 21 |
+
"num_modalities": 4,
|
| 22 |
+
"out_channels": 16,
|
| 23 |
+
"patch_size": 2,
|
| 24 |
+
"qk_rmsnorm": true,
|
| 25 |
+
"transformers_version": "4.57.0",
|
| 26 |
+
"use_goal_image": true,
|
| 27 |
+
"use_primary_goal_image_only": true,
|
| 28 |
+
"vlm_dim": 2560
|
| 29 |
+
}
|
mmflow-libero/libero-s1/30000/transformer/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5c2b1f50fc3b3dbdac4af403bd4110079b9ded6bccdb852f3154b9e44d468f6
|
| 3 |
+
size 4870539088
|
mmflow-libero/libero-s1/30000/vlm/config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"VLM"
|
| 4 |
+
],
|
| 5 |
+
"attn_implementation": "sdpa",
|
| 6 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 7 |
+
"device_map": "cuda",
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"hidden_size": 2560,
|
| 10 |
+
"load_in_4bit": true,
|
| 11 |
+
"load_in_8bit": false,
|
| 12 |
+
"max_new_tokens": 1024,
|
| 13 |
+
"max_tokens": 300,
|
| 14 |
+
"model_dtype": "bfloat16",
|
| 15 |
+
"model_id": "Qwen/Qwen3-VL-4B-Instruct",
|
| 16 |
+
"model_type": "vlm",
|
| 17 |
+
"system_prompt": "\nYou're a robot visual perception module for robot manipulation.\n\n## Inputs:\n<image_1>: head camera (primary view)\n<image_2>: left wrist camera, valid only if left_cam_present = true\n<image_3>: right wrist camera, valid only if right_cam_present = true\n\n## Rules:\n- Ignore any wrist image whose present flag is false.\n- Do not infer information from missing cameras.\n- Base all understanding on visible evidence only.\n\n## Objective:\nEncode objects, spatial relations, and manipulation-relevant affordances.\n",
|
| 18 |
+
"transformers_version": "4.57.0",
|
| 19 |
+
"trust_remote_code": true,
|
| 20 |
+
"use_double_quant": false,
|
| 21 |
+
"use_nf4": false
|
| 22 |
+
}
|
mmflow-libero/libero-s1/30000/vlm/inner_model/added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
mmflow-libero/libero-s1/30000/vlm/inner_model/chat_template.jinja
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{%- if messages[0].content is string %}
|
| 5 |
+
{{- messages[0].content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for content in messages[0].content %}
|
| 8 |
+
{%- if 'text' in content %}
|
| 9 |
+
{{- content.text }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- '\n\n' }}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{{- "# 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>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "\n" }}
|
| 18 |
+
{{- tool | tojson }}
|
| 19 |
+
{%- endfor %}
|
| 20 |
+
{{- "\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" }}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{%- if messages[0].role == 'system' %}
|
| 23 |
+
{{- '<|im_start|>system\n' }}
|
| 24 |
+
{%- if messages[0].content is string %}
|
| 25 |
+
{{- messages[0].content }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- for content in messages[0].content %}
|
| 28 |
+
{%- if 'text' in content %}
|
| 29 |
+
{{- content.text }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_end|>\n' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set image_count = namespace(value=0) %}
|
| 37 |
+
{%- set video_count = namespace(value=0) %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.role == "user" %}
|
| 40 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 41 |
+
{%- if message.content is string %}
|
| 42 |
+
{{- message.content }}
|
| 43 |
+
{%- else %}
|
| 44 |
+
{%- for content in message.content %}
|
| 45 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 46 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 47 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 48 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 49 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 50 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 51 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 52 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 53 |
+
{%- elif 'text' in content %}
|
| 54 |
+
{{- content.text }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{{- '<|im_end|>\n' }}
|
| 59 |
+
{%- elif message.role == "assistant" %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 61 |
+
{%- if message.content is string %}
|
| 62 |
+
{{- message.content }}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- for content_item in message.content %}
|
| 65 |
+
{%- if 'text' in content_item %}
|
| 66 |
+
{{- content_item.text }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- endfor %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if message.tool_calls %}
|
| 71 |
+
{%- for tool_call in message.tool_calls %}
|
| 72 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 73 |
+
{{- '\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if tool_call.function %}
|
| 76 |
+
{%- set tool_call = tool_call.function %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 79 |
+
{{- tool_call.name }}
|
| 80 |
+
{{- '", "arguments": ' }}
|
| 81 |
+
{%- if tool_call.arguments is string %}
|
| 82 |
+
{{- tool_call.arguments }}
|
| 83 |
+
{%- else %}
|
| 84 |
+
{{- tool_call.arguments | tojson }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '}\n</tool_call>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '<|im_end|>\n' }}
|
| 90 |
+
{%- elif message.role == "tool" %}
|
| 91 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 92 |
+
{{- '<|im_start|>user' }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '\n<tool_response>\n' }}
|
| 95 |
+
{%- if message.content is string %}
|
| 96 |
+
{{- message.content }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- for content in message.content %}
|
| 99 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 100 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 101 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 102 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 103 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 104 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 105 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 106 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 107 |
+
{%- elif 'text' in content %}
|
| 108 |
+
{{- content.text }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endfor %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '\n</tool_response>' }}
|
| 113 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 114 |
+
{{- '<|im_end|>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endfor %}
|
| 118 |
+
{%- if add_generation_prompt %}
|
| 119 |
+
{{- '<|im_start|>assistant\n' }}
|
| 120 |
+
{%- endif %}
|
mmflow-libero/libero-s1/30000/vlm/inner_model/config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 151655,
|
| 7 |
+
"model_type": "qwen3_vl",
|
| 8 |
+
"quantization_config": {
|
| 9 |
+
"_load_in_4bit": true,
|
| 10 |
+
"_load_in_8bit": false,
|
| 11 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 12 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 13 |
+
"bnb_4bit_quant_type": "fp4",
|
| 14 |
+
"bnb_4bit_use_double_quant": false,
|
| 15 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 16 |
+
"llm_int8_has_fp16_weight": false,
|
| 17 |
+
"llm_int8_skip_modules": null,
|
| 18 |
+
"llm_int8_threshold": 6.0,
|
| 19 |
+
"load_in_4bit": true,
|
| 20 |
+
"load_in_8bit": false,
|
| 21 |
+
"quant_method": "bitsandbytes"
|
| 22 |
+
},
|
| 23 |
+
"text_config": {
|
| 24 |
+
"attention_bias": false,
|
| 25 |
+
"attention_dropout": 0.0,
|
| 26 |
+
"bos_token_id": 151643,
|
| 27 |
+
"dtype": "bfloat16",
|
| 28 |
+
"eos_token_id": 151645,
|
| 29 |
+
"head_dim": 128,
|
| 30 |
+
"hidden_act": "silu",
|
| 31 |
+
"hidden_size": 2560,
|
| 32 |
+
"initializer_range": 0.02,
|
| 33 |
+
"intermediate_size": 9728,
|
| 34 |
+
"max_position_embeddings": 262144,
|
| 35 |
+
"model_type": "qwen3_vl_text",
|
| 36 |
+
"num_attention_heads": 32,
|
| 37 |
+
"num_hidden_layers": 36,
|
| 38 |
+
"num_key_value_heads": 8,
|
| 39 |
+
"rms_norm_eps": 1e-06,
|
| 40 |
+
"rope_scaling": {
|
| 41 |
+
"mrope_interleaved": true,
|
| 42 |
+
"mrope_section": [
|
| 43 |
+
24,
|
| 44 |
+
20,
|
| 45 |
+
20
|
| 46 |
+
],
|
| 47 |
+
"rope_type": "default"
|
| 48 |
+
},
|
| 49 |
+
"rope_theta": 5000000,
|
| 50 |
+
"tie_word_embeddings": true,
|
| 51 |
+
"use_cache": true,
|
| 52 |
+
"vocab_size": 151936
|
| 53 |
+
},
|
| 54 |
+
"tie_word_embeddings": true,
|
| 55 |
+
"transformers_version": "4.57.0",
|
| 56 |
+
"video_token_id": 151656,
|
| 57 |
+
"vision_config": {
|
| 58 |
+
"deepstack_visual_indexes": [
|
| 59 |
+
5,
|
| 60 |
+
11,
|
| 61 |
+
17
|
| 62 |
+
],
|
| 63 |
+
"depth": 24,
|
| 64 |
+
"dtype": "bfloat16",
|
| 65 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 66 |
+
"hidden_size": 1024,
|
| 67 |
+
"in_channels": 3,
|
| 68 |
+
"initializer_range": 0.02,
|
| 69 |
+
"intermediate_size": 4096,
|
| 70 |
+
"model_type": "qwen3_vl",
|
| 71 |
+
"num_heads": 16,
|
| 72 |
+
"num_position_embeddings": 2304,
|
| 73 |
+
"out_hidden_size": 2560,
|
| 74 |
+
"patch_size": 16,
|
| 75 |
+
"spatial_merge_size": 2,
|
| 76 |
+
"temporal_patch_size": 2
|
| 77 |
+
},
|
| 78 |
+
"vision_end_token_id": 151653,
|
| 79 |
+
"vision_start_token_id": 151652
|
| 80 |
+
}
|
mmflow-libero/libero-s1/30000/vlm/inner_model/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": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.0"
|
| 13 |
+
}
|
mmflow-libero/libero-s1/30000/vlm/inner_model/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mmflow-libero/libero-s1/30000/vlm/inner_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d2f77bc5423bd80ad85880cf6e259928e9e69ef71953460ad767b31092ab09e
|
| 3 |
+
size 3062596856
|
mmflow-libero/libero-s1/30000/vlm/inner_model/preprocessor_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"disable_grouping": null,
|
| 7 |
+
"do_center_crop": null,
|
| 8 |
+
"do_convert_rgb": true,
|
| 9 |
+
"do_normalize": true,
|
| 10 |
+
"do_pad": null,
|
| 11 |
+
"do_rescale": true,
|
| 12 |
+
"do_resize": true,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 19 |
+
"image_std": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"input_data_format": null,
|
| 25 |
+
"max_pixels": null,
|
| 26 |
+
"merge_size": 2,
|
| 27 |
+
"min_pixels": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_tensors": null,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 16777216,
|
| 36 |
+
"shortest_edge": 65536
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2
|
| 39 |
+
}
|
mmflow-libero/libero-s1/30000/vlm/inner_model/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 |
+
}
|
mmflow-libero/libero-s1/30000/vlm/inner_model/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffef306165070c2b77d0fc1a4ff3981511a8049b13e6fb91b0f6613ec5ab7d01
|
| 3 |
+
size 11422932
|
mmflow-libero/libero-s1/30000/vlm/inner_model/tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"processor_class": "Qwen3VLProcessor",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
mmflow-libero/libero-s1/30000/vlm/inner_model/video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"do_sample_frames": true,
|
| 12 |
+
"fps": 2,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_frames": 768,
|
| 25 |
+
"merge_size": 2,
|
| 26 |
+
"min_frames": 4,
|
| 27 |
+
"num_frames": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_metadata": false,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 25165824,
|
| 36 |
+
"shortest_edge": 4096
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2,
|
| 39 |
+
"video_metadata": null,
|
| 40 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 41 |
+
}
|
mmflow-libero/libero-s1/30000/vlm/inner_model/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mmflow-libero/libero-s1/30000/vlm/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57df2f63d620a6e211732eb7dee3a178cc53223bba29b690935a6d47ec50fb2f
|
| 3 |
+
size 3062607544
|
mmflow-libero/libero-s1/trainable_parameters.txt
ADDED
|
@@ -0,0 +1,910 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Trainable parameter dump
|
| 2 |
+
total_numel=3760102467
|
| 3 |
+
trainable_numel=22110976
|
| 4 |
+
trainable_ratio=0.00588042
|
| 5 |
+
trainable_tensor_count=904
|
| 6 |
+
|
| 7 |
+
transformer.in_proj_text.lora_A.default.weight shape=(16x2560) numel=40960
|
| 8 |
+
transformer.in_proj_text.lora_B.default.weight shape=(768x16) numel=12288
|
| 9 |
+
transformer.in_proj_state.lora_A.default.weight shape=(16x16) numel=256
|
| 10 |
+
transformer.in_proj_state.lora_B.default.weight shape=(768x16) numel=12288
|
| 11 |
+
transformer.in_proj_action.lora_A.default.weight shape=(16x16) numel=256
|
| 12 |
+
transformer.in_proj_action.lora_B.default.weight shape=(768x16) numel=12288
|
| 13 |
+
transformer.out_action.linear.lora_A.default.weight shape=(16x768) numel=12288
|
| 14 |
+
transformer.out_action.linear.lora_B.default.weight shape=(16x16) numel=256
|
| 15 |
+
transformer.mmdit.blocks.0.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 16 |
+
transformer.mmdit.blocks.0.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 17 |
+
transformer.mmdit.blocks.0.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 18 |
+
transformer.mmdit.blocks.0.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 19 |
+
transformer.mmdit.blocks.0.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 20 |
+
transformer.mmdit.blocks.0.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 21 |
+
transformer.mmdit.blocks.0.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 22 |
+
transformer.mmdit.blocks.0.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 23 |
+
transformer.mmdit.blocks.0.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 24 |
+
transformer.mmdit.blocks.0.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 25 |
+
transformer.mmdit.blocks.0.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 26 |
+
transformer.mmdit.blocks.0.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 27 |
+
transformer.mmdit.blocks.0.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 28 |
+
transformer.mmdit.blocks.0.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 29 |
+
transformer.mmdit.blocks.0.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 30 |
+
transformer.mmdit.blocks.0.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 31 |
+
transformer.mmdit.blocks.0.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 32 |
+
transformer.mmdit.blocks.0.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 33 |
+
transformer.mmdit.blocks.0.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 34 |
+
transformer.mmdit.blocks.0.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 35 |
+
transformer.mmdit.blocks.0.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 36 |
+
transformer.mmdit.blocks.0.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 37 |
+
transformer.mmdit.blocks.0.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 38 |
+
transformer.mmdit.blocks.0.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 39 |
+
transformer.mmdit.blocks.0.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 40 |
+
transformer.mmdit.blocks.0.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 41 |
+
transformer.mmdit.blocks.0.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 42 |
+
transformer.mmdit.blocks.0.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 43 |
+
transformer.mmdit.blocks.0.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 44 |
+
transformer.mmdit.blocks.0.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 45 |
+
transformer.mmdit.blocks.0.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 46 |
+
transformer.mmdit.blocks.0.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 47 |
+
transformer.mmdit.blocks.1.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 48 |
+
transformer.mmdit.blocks.1.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 49 |
+
transformer.mmdit.blocks.1.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 50 |
+
transformer.mmdit.blocks.1.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 51 |
+
transformer.mmdit.blocks.1.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 52 |
+
transformer.mmdit.blocks.1.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 53 |
+
transformer.mmdit.blocks.1.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 54 |
+
transformer.mmdit.blocks.1.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 55 |
+
transformer.mmdit.blocks.1.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 56 |
+
transformer.mmdit.blocks.1.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 57 |
+
transformer.mmdit.blocks.1.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 58 |
+
transformer.mmdit.blocks.1.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 59 |
+
transformer.mmdit.blocks.1.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 60 |
+
transformer.mmdit.blocks.1.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 61 |
+
transformer.mmdit.blocks.1.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 62 |
+
transformer.mmdit.blocks.1.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 63 |
+
transformer.mmdit.blocks.1.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 64 |
+
transformer.mmdit.blocks.1.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 65 |
+
transformer.mmdit.blocks.1.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 66 |
+
transformer.mmdit.blocks.1.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 67 |
+
transformer.mmdit.blocks.1.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 68 |
+
transformer.mmdit.blocks.1.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 69 |
+
transformer.mmdit.blocks.1.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 70 |
+
transformer.mmdit.blocks.1.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 71 |
+
transformer.mmdit.blocks.1.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 72 |
+
transformer.mmdit.blocks.1.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 73 |
+
transformer.mmdit.blocks.1.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 74 |
+
transformer.mmdit.blocks.1.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 75 |
+
transformer.mmdit.blocks.1.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 76 |
+
transformer.mmdit.blocks.1.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 77 |
+
transformer.mmdit.blocks.1.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 78 |
+
transformer.mmdit.blocks.1.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 79 |
+
transformer.mmdit.blocks.2.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 80 |
+
transformer.mmdit.blocks.2.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 81 |
+
transformer.mmdit.blocks.2.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 82 |
+
transformer.mmdit.blocks.2.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 83 |
+
transformer.mmdit.blocks.2.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 84 |
+
transformer.mmdit.blocks.2.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 85 |
+
transformer.mmdit.blocks.2.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 86 |
+
transformer.mmdit.blocks.2.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 87 |
+
transformer.mmdit.blocks.2.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 88 |
+
transformer.mmdit.blocks.2.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 89 |
+
transformer.mmdit.blocks.2.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 90 |
+
transformer.mmdit.blocks.2.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 91 |
+
transformer.mmdit.blocks.2.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 92 |
+
transformer.mmdit.blocks.2.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 93 |
+
transformer.mmdit.blocks.2.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 94 |
+
transformer.mmdit.blocks.2.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 95 |
+
transformer.mmdit.blocks.2.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 96 |
+
transformer.mmdit.blocks.2.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 97 |
+
transformer.mmdit.blocks.2.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 98 |
+
transformer.mmdit.blocks.2.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 99 |
+
transformer.mmdit.blocks.2.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 100 |
+
transformer.mmdit.blocks.2.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 101 |
+
transformer.mmdit.blocks.2.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 102 |
+
transformer.mmdit.blocks.2.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 103 |
+
transformer.mmdit.blocks.2.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 104 |
+
transformer.mmdit.blocks.2.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 105 |
+
transformer.mmdit.blocks.2.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 106 |
+
transformer.mmdit.blocks.2.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 107 |
+
transformer.mmdit.blocks.2.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 108 |
+
transformer.mmdit.blocks.2.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 109 |
+
transformer.mmdit.blocks.2.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 110 |
+
transformer.mmdit.blocks.2.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 111 |
+
transformer.mmdit.blocks.3.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 112 |
+
transformer.mmdit.blocks.3.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 113 |
+
transformer.mmdit.blocks.3.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 114 |
+
transformer.mmdit.blocks.3.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 115 |
+
transformer.mmdit.blocks.3.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 116 |
+
transformer.mmdit.blocks.3.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 117 |
+
transformer.mmdit.blocks.3.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 118 |
+
transformer.mmdit.blocks.3.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 119 |
+
transformer.mmdit.blocks.3.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 120 |
+
transformer.mmdit.blocks.3.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 121 |
+
transformer.mmdit.blocks.3.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 122 |
+
transformer.mmdit.blocks.3.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 123 |
+
transformer.mmdit.blocks.3.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 124 |
+
transformer.mmdit.blocks.3.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 125 |
+
transformer.mmdit.blocks.3.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 126 |
+
transformer.mmdit.blocks.3.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 127 |
+
transformer.mmdit.blocks.3.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 128 |
+
transformer.mmdit.blocks.3.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 129 |
+
transformer.mmdit.blocks.3.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 130 |
+
transformer.mmdit.blocks.3.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 131 |
+
transformer.mmdit.blocks.3.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 132 |
+
transformer.mmdit.blocks.3.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 133 |
+
transformer.mmdit.blocks.3.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 134 |
+
transformer.mmdit.blocks.3.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 135 |
+
transformer.mmdit.blocks.3.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 136 |
+
transformer.mmdit.blocks.3.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 137 |
+
transformer.mmdit.blocks.3.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 138 |
+
transformer.mmdit.blocks.3.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 139 |
+
transformer.mmdit.blocks.3.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 140 |
+
transformer.mmdit.blocks.3.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 141 |
+
transformer.mmdit.blocks.3.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 142 |
+
transformer.mmdit.blocks.3.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 143 |
+
transformer.mmdit.blocks.4.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 144 |
+
transformer.mmdit.blocks.4.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 145 |
+
transformer.mmdit.blocks.4.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 146 |
+
transformer.mmdit.blocks.4.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 147 |
+
transformer.mmdit.blocks.4.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 148 |
+
transformer.mmdit.blocks.4.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 149 |
+
transformer.mmdit.blocks.4.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 150 |
+
transformer.mmdit.blocks.4.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 151 |
+
transformer.mmdit.blocks.4.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 152 |
+
transformer.mmdit.blocks.4.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 153 |
+
transformer.mmdit.blocks.4.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 154 |
+
transformer.mmdit.blocks.4.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 155 |
+
transformer.mmdit.blocks.4.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 156 |
+
transformer.mmdit.blocks.4.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 157 |
+
transformer.mmdit.blocks.4.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 158 |
+
transformer.mmdit.blocks.4.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 159 |
+
transformer.mmdit.blocks.4.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 160 |
+
transformer.mmdit.blocks.4.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 161 |
+
transformer.mmdit.blocks.4.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 162 |
+
transformer.mmdit.blocks.4.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 163 |
+
transformer.mmdit.blocks.4.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 164 |
+
transformer.mmdit.blocks.4.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 165 |
+
transformer.mmdit.blocks.4.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 166 |
+
transformer.mmdit.blocks.4.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 167 |
+
transformer.mmdit.blocks.4.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 168 |
+
transformer.mmdit.blocks.4.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 169 |
+
transformer.mmdit.blocks.4.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 170 |
+
transformer.mmdit.blocks.4.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 171 |
+
transformer.mmdit.blocks.4.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 172 |
+
transformer.mmdit.blocks.4.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 173 |
+
transformer.mmdit.blocks.4.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 174 |
+
transformer.mmdit.blocks.4.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 175 |
+
transformer.mmdit.blocks.5.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 176 |
+
transformer.mmdit.blocks.5.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 177 |
+
transformer.mmdit.blocks.5.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 178 |
+
transformer.mmdit.blocks.5.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 179 |
+
transformer.mmdit.blocks.5.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 180 |
+
transformer.mmdit.blocks.5.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 181 |
+
transformer.mmdit.blocks.5.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 182 |
+
transformer.mmdit.blocks.5.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 183 |
+
transformer.mmdit.blocks.5.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 184 |
+
transformer.mmdit.blocks.5.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 185 |
+
transformer.mmdit.blocks.5.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 186 |
+
transformer.mmdit.blocks.5.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 187 |
+
transformer.mmdit.blocks.5.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 188 |
+
transformer.mmdit.blocks.5.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 189 |
+
transformer.mmdit.blocks.5.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 190 |
+
transformer.mmdit.blocks.5.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 191 |
+
transformer.mmdit.blocks.5.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 192 |
+
transformer.mmdit.blocks.5.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 193 |
+
transformer.mmdit.blocks.5.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 194 |
+
transformer.mmdit.blocks.5.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 195 |
+
transformer.mmdit.blocks.5.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 196 |
+
transformer.mmdit.blocks.5.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 197 |
+
transformer.mmdit.blocks.5.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 198 |
+
transformer.mmdit.blocks.5.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 199 |
+
transformer.mmdit.blocks.5.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 200 |
+
transformer.mmdit.blocks.5.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 201 |
+
transformer.mmdit.blocks.5.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 202 |
+
transformer.mmdit.blocks.5.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 203 |
+
transformer.mmdit.blocks.5.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 204 |
+
transformer.mmdit.blocks.5.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 205 |
+
transformer.mmdit.blocks.5.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 206 |
+
transformer.mmdit.blocks.5.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 207 |
+
transformer.mmdit.blocks.6.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 208 |
+
transformer.mmdit.blocks.6.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 209 |
+
transformer.mmdit.blocks.6.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 210 |
+
transformer.mmdit.blocks.6.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 211 |
+
transformer.mmdit.blocks.6.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 212 |
+
transformer.mmdit.blocks.6.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 213 |
+
transformer.mmdit.blocks.6.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 214 |
+
transformer.mmdit.blocks.6.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 215 |
+
transformer.mmdit.blocks.6.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 216 |
+
transformer.mmdit.blocks.6.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 217 |
+
transformer.mmdit.blocks.6.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 218 |
+
transformer.mmdit.blocks.6.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 219 |
+
transformer.mmdit.blocks.6.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 220 |
+
transformer.mmdit.blocks.6.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 221 |
+
transformer.mmdit.blocks.6.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 222 |
+
transformer.mmdit.blocks.6.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 223 |
+
transformer.mmdit.blocks.6.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 224 |
+
transformer.mmdit.blocks.6.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 225 |
+
transformer.mmdit.blocks.6.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 226 |
+
transformer.mmdit.blocks.6.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 227 |
+
transformer.mmdit.blocks.6.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 228 |
+
transformer.mmdit.blocks.6.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 229 |
+
transformer.mmdit.blocks.6.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 230 |
+
transformer.mmdit.blocks.6.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 231 |
+
transformer.mmdit.blocks.6.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 232 |
+
transformer.mmdit.blocks.6.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 233 |
+
transformer.mmdit.blocks.6.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 234 |
+
transformer.mmdit.blocks.6.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 235 |
+
transformer.mmdit.blocks.6.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 236 |
+
transformer.mmdit.blocks.6.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 237 |
+
transformer.mmdit.blocks.6.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 238 |
+
transformer.mmdit.blocks.6.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 239 |
+
transformer.mmdit.blocks.7.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 240 |
+
transformer.mmdit.blocks.7.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 241 |
+
transformer.mmdit.blocks.7.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 242 |
+
transformer.mmdit.blocks.7.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 243 |
+
transformer.mmdit.blocks.7.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 244 |
+
transformer.mmdit.blocks.7.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 245 |
+
transformer.mmdit.blocks.7.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 246 |
+
transformer.mmdit.blocks.7.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 247 |
+
transformer.mmdit.blocks.7.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 248 |
+
transformer.mmdit.blocks.7.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 249 |
+
transformer.mmdit.blocks.7.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 250 |
+
transformer.mmdit.blocks.7.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 251 |
+
transformer.mmdit.blocks.7.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 252 |
+
transformer.mmdit.blocks.7.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 253 |
+
transformer.mmdit.blocks.7.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 254 |
+
transformer.mmdit.blocks.7.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 255 |
+
transformer.mmdit.blocks.7.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 256 |
+
transformer.mmdit.blocks.7.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 257 |
+
transformer.mmdit.blocks.7.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 258 |
+
transformer.mmdit.blocks.7.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 259 |
+
transformer.mmdit.blocks.7.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 260 |
+
transformer.mmdit.blocks.7.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 261 |
+
transformer.mmdit.blocks.7.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 262 |
+
transformer.mmdit.blocks.7.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 263 |
+
transformer.mmdit.blocks.7.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 264 |
+
transformer.mmdit.blocks.7.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 265 |
+
transformer.mmdit.blocks.7.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 266 |
+
transformer.mmdit.blocks.7.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 267 |
+
transformer.mmdit.blocks.7.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 268 |
+
transformer.mmdit.blocks.7.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 269 |
+
transformer.mmdit.blocks.7.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 270 |
+
transformer.mmdit.blocks.7.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 271 |
+
transformer.mmdit.blocks.8.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 272 |
+
transformer.mmdit.blocks.8.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 273 |
+
transformer.mmdit.blocks.8.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 274 |
+
transformer.mmdit.blocks.8.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 275 |
+
transformer.mmdit.blocks.8.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 276 |
+
transformer.mmdit.blocks.8.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 277 |
+
transformer.mmdit.blocks.8.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 278 |
+
transformer.mmdit.blocks.8.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 279 |
+
transformer.mmdit.blocks.8.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 280 |
+
transformer.mmdit.blocks.8.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 281 |
+
transformer.mmdit.blocks.8.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 282 |
+
transformer.mmdit.blocks.8.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 283 |
+
transformer.mmdit.blocks.8.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 284 |
+
transformer.mmdit.blocks.8.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 285 |
+
transformer.mmdit.blocks.8.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 286 |
+
transformer.mmdit.blocks.8.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 287 |
+
transformer.mmdit.blocks.8.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 288 |
+
transformer.mmdit.blocks.8.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 289 |
+
transformer.mmdit.blocks.8.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 290 |
+
transformer.mmdit.blocks.8.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 291 |
+
transformer.mmdit.blocks.8.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 292 |
+
transformer.mmdit.blocks.8.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 293 |
+
transformer.mmdit.blocks.8.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 294 |
+
transformer.mmdit.blocks.8.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 295 |
+
transformer.mmdit.blocks.8.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 296 |
+
transformer.mmdit.blocks.8.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 297 |
+
transformer.mmdit.blocks.8.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 298 |
+
transformer.mmdit.blocks.8.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 299 |
+
transformer.mmdit.blocks.8.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 300 |
+
transformer.mmdit.blocks.8.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 301 |
+
transformer.mmdit.blocks.8.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 302 |
+
transformer.mmdit.blocks.8.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 303 |
+
transformer.mmdit.blocks.9.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 304 |
+
transformer.mmdit.blocks.9.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 305 |
+
transformer.mmdit.blocks.9.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 306 |
+
transformer.mmdit.blocks.9.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 307 |
+
transformer.mmdit.blocks.9.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 308 |
+
transformer.mmdit.blocks.9.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 309 |
+
transformer.mmdit.blocks.9.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 310 |
+
transformer.mmdit.blocks.9.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 311 |
+
transformer.mmdit.blocks.9.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 312 |
+
transformer.mmdit.blocks.9.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 313 |
+
transformer.mmdit.blocks.9.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 314 |
+
transformer.mmdit.blocks.9.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 315 |
+
transformer.mmdit.blocks.9.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 316 |
+
transformer.mmdit.blocks.9.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 317 |
+
transformer.mmdit.blocks.9.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 318 |
+
transformer.mmdit.blocks.9.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 319 |
+
transformer.mmdit.blocks.9.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 320 |
+
transformer.mmdit.blocks.9.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 321 |
+
transformer.mmdit.blocks.9.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 322 |
+
transformer.mmdit.blocks.9.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 323 |
+
transformer.mmdit.blocks.9.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 324 |
+
transformer.mmdit.blocks.9.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 325 |
+
transformer.mmdit.blocks.9.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 326 |
+
transformer.mmdit.blocks.9.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 327 |
+
transformer.mmdit.blocks.9.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 328 |
+
transformer.mmdit.blocks.9.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 329 |
+
transformer.mmdit.blocks.9.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 330 |
+
transformer.mmdit.blocks.9.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 331 |
+
transformer.mmdit.blocks.9.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 332 |
+
transformer.mmdit.blocks.9.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 333 |
+
transformer.mmdit.blocks.9.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 334 |
+
transformer.mmdit.blocks.9.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 335 |
+
transformer.mmdit.blocks.10.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 336 |
+
transformer.mmdit.blocks.10.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 337 |
+
transformer.mmdit.blocks.10.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 338 |
+
transformer.mmdit.blocks.10.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 339 |
+
transformer.mmdit.blocks.10.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 340 |
+
transformer.mmdit.blocks.10.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 341 |
+
transformer.mmdit.blocks.10.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 342 |
+
transformer.mmdit.blocks.10.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 343 |
+
transformer.mmdit.blocks.10.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 344 |
+
transformer.mmdit.blocks.10.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 345 |
+
transformer.mmdit.blocks.10.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 346 |
+
transformer.mmdit.blocks.10.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 347 |
+
transformer.mmdit.blocks.10.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 348 |
+
transformer.mmdit.blocks.10.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 349 |
+
transformer.mmdit.blocks.10.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 350 |
+
transformer.mmdit.blocks.10.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 351 |
+
transformer.mmdit.blocks.10.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 352 |
+
transformer.mmdit.blocks.10.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 353 |
+
transformer.mmdit.blocks.10.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 354 |
+
transformer.mmdit.blocks.10.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 355 |
+
transformer.mmdit.blocks.10.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 356 |
+
transformer.mmdit.blocks.10.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 357 |
+
transformer.mmdit.blocks.10.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 358 |
+
transformer.mmdit.blocks.10.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 359 |
+
transformer.mmdit.blocks.10.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 360 |
+
transformer.mmdit.blocks.10.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 361 |
+
transformer.mmdit.blocks.10.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 362 |
+
transformer.mmdit.blocks.10.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 363 |
+
transformer.mmdit.blocks.10.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 364 |
+
transformer.mmdit.blocks.10.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 365 |
+
transformer.mmdit.blocks.10.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 366 |
+
transformer.mmdit.blocks.10.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 367 |
+
transformer.mmdit.blocks.11.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 368 |
+
transformer.mmdit.blocks.11.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 369 |
+
transformer.mmdit.blocks.11.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 370 |
+
transformer.mmdit.blocks.11.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 371 |
+
transformer.mmdit.blocks.11.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 372 |
+
transformer.mmdit.blocks.11.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 373 |
+
transformer.mmdit.blocks.11.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 374 |
+
transformer.mmdit.blocks.11.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 375 |
+
transformer.mmdit.blocks.11.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 376 |
+
transformer.mmdit.blocks.11.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 377 |
+
transformer.mmdit.blocks.11.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 378 |
+
transformer.mmdit.blocks.11.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 379 |
+
transformer.mmdit.blocks.11.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 380 |
+
transformer.mmdit.blocks.11.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 381 |
+
transformer.mmdit.blocks.11.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 382 |
+
transformer.mmdit.blocks.11.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 383 |
+
transformer.mmdit.blocks.11.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 384 |
+
transformer.mmdit.blocks.11.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 385 |
+
transformer.mmdit.blocks.11.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 386 |
+
transformer.mmdit.blocks.11.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 387 |
+
transformer.mmdit.blocks.11.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 388 |
+
transformer.mmdit.blocks.11.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 389 |
+
transformer.mmdit.blocks.11.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 390 |
+
transformer.mmdit.blocks.11.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 391 |
+
transformer.mmdit.blocks.11.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 392 |
+
transformer.mmdit.blocks.11.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 393 |
+
transformer.mmdit.blocks.11.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 394 |
+
transformer.mmdit.blocks.11.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 395 |
+
transformer.mmdit.blocks.11.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 396 |
+
transformer.mmdit.blocks.11.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 397 |
+
transformer.mmdit.blocks.11.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 398 |
+
transformer.mmdit.blocks.11.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 399 |
+
transformer.mmdit.blocks.12.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 400 |
+
transformer.mmdit.blocks.12.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 401 |
+
transformer.mmdit.blocks.12.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 402 |
+
transformer.mmdit.blocks.12.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 403 |
+
transformer.mmdit.blocks.12.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 404 |
+
transformer.mmdit.blocks.12.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 405 |
+
transformer.mmdit.blocks.12.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 406 |
+
transformer.mmdit.blocks.12.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 407 |
+
transformer.mmdit.blocks.12.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 408 |
+
transformer.mmdit.blocks.12.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 409 |
+
transformer.mmdit.blocks.12.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 410 |
+
transformer.mmdit.blocks.12.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 411 |
+
transformer.mmdit.blocks.12.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 412 |
+
transformer.mmdit.blocks.12.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 413 |
+
transformer.mmdit.blocks.12.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 414 |
+
transformer.mmdit.blocks.12.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 415 |
+
transformer.mmdit.blocks.12.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 416 |
+
transformer.mmdit.blocks.12.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 417 |
+
transformer.mmdit.blocks.12.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 418 |
+
transformer.mmdit.blocks.12.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 419 |
+
transformer.mmdit.blocks.12.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 420 |
+
transformer.mmdit.blocks.12.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 421 |
+
transformer.mmdit.blocks.12.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 422 |
+
transformer.mmdit.blocks.12.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 423 |
+
transformer.mmdit.blocks.12.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 424 |
+
transformer.mmdit.blocks.12.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 425 |
+
transformer.mmdit.blocks.12.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 426 |
+
transformer.mmdit.blocks.12.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 427 |
+
transformer.mmdit.blocks.12.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 428 |
+
transformer.mmdit.blocks.12.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 429 |
+
transformer.mmdit.blocks.12.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 430 |
+
transformer.mmdit.blocks.12.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 431 |
+
transformer.mmdit.blocks.13.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 432 |
+
transformer.mmdit.blocks.13.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 433 |
+
transformer.mmdit.blocks.13.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 434 |
+
transformer.mmdit.blocks.13.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 435 |
+
transformer.mmdit.blocks.13.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 436 |
+
transformer.mmdit.blocks.13.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 437 |
+
transformer.mmdit.blocks.13.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 438 |
+
transformer.mmdit.blocks.13.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 439 |
+
transformer.mmdit.blocks.13.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 440 |
+
transformer.mmdit.blocks.13.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 441 |
+
transformer.mmdit.blocks.13.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 442 |
+
transformer.mmdit.blocks.13.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 443 |
+
transformer.mmdit.blocks.13.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 444 |
+
transformer.mmdit.blocks.13.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 445 |
+
transformer.mmdit.blocks.13.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 446 |
+
transformer.mmdit.blocks.13.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 447 |
+
transformer.mmdit.blocks.13.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 448 |
+
transformer.mmdit.blocks.13.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 449 |
+
transformer.mmdit.blocks.13.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 450 |
+
transformer.mmdit.blocks.13.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 451 |
+
transformer.mmdit.blocks.13.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 452 |
+
transformer.mmdit.blocks.13.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 453 |
+
transformer.mmdit.blocks.13.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 454 |
+
transformer.mmdit.blocks.13.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 455 |
+
transformer.mmdit.blocks.13.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 456 |
+
transformer.mmdit.blocks.13.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 457 |
+
transformer.mmdit.blocks.13.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 458 |
+
transformer.mmdit.blocks.13.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 459 |
+
transformer.mmdit.blocks.13.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 460 |
+
transformer.mmdit.blocks.13.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 461 |
+
transformer.mmdit.blocks.13.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 462 |
+
transformer.mmdit.blocks.13.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 463 |
+
transformer.mmdit.blocks.14.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 464 |
+
transformer.mmdit.blocks.14.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 465 |
+
transformer.mmdit.blocks.14.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 466 |
+
transformer.mmdit.blocks.14.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 467 |
+
transformer.mmdit.blocks.14.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 468 |
+
transformer.mmdit.blocks.14.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 469 |
+
transformer.mmdit.blocks.14.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 470 |
+
transformer.mmdit.blocks.14.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 471 |
+
transformer.mmdit.blocks.14.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 472 |
+
transformer.mmdit.blocks.14.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 473 |
+
transformer.mmdit.blocks.14.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 474 |
+
transformer.mmdit.blocks.14.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 475 |
+
transformer.mmdit.blocks.14.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 476 |
+
transformer.mmdit.blocks.14.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 477 |
+
transformer.mmdit.blocks.14.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 478 |
+
transformer.mmdit.blocks.14.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 479 |
+
transformer.mmdit.blocks.14.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 480 |
+
transformer.mmdit.blocks.14.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 481 |
+
transformer.mmdit.blocks.14.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 482 |
+
transformer.mmdit.blocks.14.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 483 |
+
transformer.mmdit.blocks.14.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 484 |
+
transformer.mmdit.blocks.14.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 485 |
+
transformer.mmdit.blocks.14.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 486 |
+
transformer.mmdit.blocks.14.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 487 |
+
transformer.mmdit.blocks.14.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 488 |
+
transformer.mmdit.blocks.14.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 489 |
+
transformer.mmdit.blocks.14.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 490 |
+
transformer.mmdit.blocks.14.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 491 |
+
transformer.mmdit.blocks.14.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 492 |
+
transformer.mmdit.blocks.14.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 493 |
+
transformer.mmdit.blocks.14.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 494 |
+
transformer.mmdit.blocks.14.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 495 |
+
transformer.mmdit.blocks.15.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 496 |
+
transformer.mmdit.blocks.15.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 497 |
+
transformer.mmdit.blocks.15.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 498 |
+
transformer.mmdit.blocks.15.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 499 |
+
transformer.mmdit.blocks.15.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 500 |
+
transformer.mmdit.blocks.15.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 501 |
+
transformer.mmdit.blocks.15.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 502 |
+
transformer.mmdit.blocks.15.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 503 |
+
transformer.mmdit.blocks.15.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 504 |
+
transformer.mmdit.blocks.15.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 505 |
+
transformer.mmdit.blocks.15.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 506 |
+
transformer.mmdit.blocks.15.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 507 |
+
transformer.mmdit.blocks.15.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 508 |
+
transformer.mmdit.blocks.15.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 509 |
+
transformer.mmdit.blocks.15.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 510 |
+
transformer.mmdit.blocks.15.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 511 |
+
transformer.mmdit.blocks.15.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 512 |
+
transformer.mmdit.blocks.15.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 513 |
+
transformer.mmdit.blocks.15.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 514 |
+
transformer.mmdit.blocks.15.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 515 |
+
transformer.mmdit.blocks.15.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 516 |
+
transformer.mmdit.blocks.15.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 517 |
+
transformer.mmdit.blocks.15.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 518 |
+
transformer.mmdit.blocks.15.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 519 |
+
transformer.mmdit.blocks.15.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 520 |
+
transformer.mmdit.blocks.15.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 521 |
+
transformer.mmdit.blocks.15.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 522 |
+
transformer.mmdit.blocks.15.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 523 |
+
transformer.mmdit.blocks.15.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 524 |
+
transformer.mmdit.blocks.15.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 525 |
+
transformer.mmdit.blocks.15.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 526 |
+
transformer.mmdit.blocks.15.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 527 |
+
transformer.mmdit.blocks.16.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 528 |
+
transformer.mmdit.blocks.16.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 529 |
+
transformer.mmdit.blocks.16.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 530 |
+
transformer.mmdit.blocks.16.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 531 |
+
transformer.mmdit.blocks.16.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 532 |
+
transformer.mmdit.blocks.16.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 533 |
+
transformer.mmdit.blocks.16.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 534 |
+
transformer.mmdit.blocks.16.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 535 |
+
transformer.mmdit.blocks.16.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 536 |
+
transformer.mmdit.blocks.16.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 537 |
+
transformer.mmdit.blocks.16.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 538 |
+
transformer.mmdit.blocks.16.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 539 |
+
transformer.mmdit.blocks.16.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 540 |
+
transformer.mmdit.blocks.16.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 541 |
+
transformer.mmdit.blocks.16.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 542 |
+
transformer.mmdit.blocks.16.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 543 |
+
transformer.mmdit.blocks.16.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 544 |
+
transformer.mmdit.blocks.16.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 545 |
+
transformer.mmdit.blocks.16.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 546 |
+
transformer.mmdit.blocks.16.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 547 |
+
transformer.mmdit.blocks.16.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 548 |
+
transformer.mmdit.blocks.16.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 549 |
+
transformer.mmdit.blocks.16.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 550 |
+
transformer.mmdit.blocks.16.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 551 |
+
transformer.mmdit.blocks.16.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 552 |
+
transformer.mmdit.blocks.16.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 553 |
+
transformer.mmdit.blocks.16.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 554 |
+
transformer.mmdit.blocks.16.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 555 |
+
transformer.mmdit.blocks.16.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 556 |
+
transformer.mmdit.blocks.16.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 557 |
+
transformer.mmdit.blocks.16.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 558 |
+
transformer.mmdit.blocks.16.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 559 |
+
transformer.mmdit.blocks.17.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 560 |
+
transformer.mmdit.blocks.17.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 561 |
+
transformer.mmdit.blocks.17.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 562 |
+
transformer.mmdit.blocks.17.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 563 |
+
transformer.mmdit.blocks.17.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 564 |
+
transformer.mmdit.blocks.17.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 565 |
+
transformer.mmdit.blocks.17.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 566 |
+
transformer.mmdit.blocks.17.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 567 |
+
transformer.mmdit.blocks.17.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 568 |
+
transformer.mmdit.blocks.17.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 569 |
+
transformer.mmdit.blocks.17.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 570 |
+
transformer.mmdit.blocks.17.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 571 |
+
transformer.mmdit.blocks.17.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 572 |
+
transformer.mmdit.blocks.17.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 573 |
+
transformer.mmdit.blocks.17.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 574 |
+
transformer.mmdit.blocks.17.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 575 |
+
transformer.mmdit.blocks.17.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 576 |
+
transformer.mmdit.blocks.17.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 577 |
+
transformer.mmdit.blocks.17.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 578 |
+
transformer.mmdit.blocks.17.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 579 |
+
transformer.mmdit.blocks.17.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 580 |
+
transformer.mmdit.blocks.17.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 581 |
+
transformer.mmdit.blocks.17.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 582 |
+
transformer.mmdit.blocks.17.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 583 |
+
transformer.mmdit.blocks.17.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 584 |
+
transformer.mmdit.blocks.17.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 585 |
+
transformer.mmdit.blocks.17.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 586 |
+
transformer.mmdit.blocks.17.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 587 |
+
transformer.mmdit.blocks.17.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 588 |
+
transformer.mmdit.blocks.17.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 589 |
+
transformer.mmdit.blocks.17.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 590 |
+
transformer.mmdit.blocks.17.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 591 |
+
transformer.mmdit.blocks.18.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 592 |
+
transformer.mmdit.blocks.18.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 593 |
+
transformer.mmdit.blocks.18.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 594 |
+
transformer.mmdit.blocks.18.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 595 |
+
transformer.mmdit.blocks.18.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 596 |
+
transformer.mmdit.blocks.18.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 597 |
+
transformer.mmdit.blocks.18.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 598 |
+
transformer.mmdit.blocks.18.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 599 |
+
transformer.mmdit.blocks.18.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 600 |
+
transformer.mmdit.blocks.18.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 601 |
+
transformer.mmdit.blocks.18.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 602 |
+
transformer.mmdit.blocks.18.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 603 |
+
transformer.mmdit.blocks.18.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 604 |
+
transformer.mmdit.blocks.18.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 605 |
+
transformer.mmdit.blocks.18.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 606 |
+
transformer.mmdit.blocks.18.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 607 |
+
transformer.mmdit.blocks.18.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 608 |
+
transformer.mmdit.blocks.18.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 609 |
+
transformer.mmdit.blocks.18.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 610 |
+
transformer.mmdit.blocks.18.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 611 |
+
transformer.mmdit.blocks.18.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 612 |
+
transformer.mmdit.blocks.18.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 613 |
+
transformer.mmdit.blocks.18.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 614 |
+
transformer.mmdit.blocks.18.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 615 |
+
transformer.mmdit.blocks.18.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 616 |
+
transformer.mmdit.blocks.18.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 617 |
+
transformer.mmdit.blocks.18.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 618 |
+
transformer.mmdit.blocks.18.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 619 |
+
transformer.mmdit.blocks.18.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 620 |
+
transformer.mmdit.blocks.18.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 621 |
+
transformer.mmdit.blocks.18.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 622 |
+
transformer.mmdit.blocks.18.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 623 |
+
transformer.mmdit.blocks.19.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 624 |
+
transformer.mmdit.blocks.19.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 625 |
+
transformer.mmdit.blocks.19.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 626 |
+
transformer.mmdit.blocks.19.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 627 |
+
transformer.mmdit.blocks.19.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 628 |
+
transformer.mmdit.blocks.19.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 629 |
+
transformer.mmdit.blocks.19.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 630 |
+
transformer.mmdit.blocks.19.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 631 |
+
transformer.mmdit.blocks.19.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 632 |
+
transformer.mmdit.blocks.19.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 633 |
+
transformer.mmdit.blocks.19.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 634 |
+
transformer.mmdit.blocks.19.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 635 |
+
transformer.mmdit.blocks.19.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 636 |
+
transformer.mmdit.blocks.19.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 637 |
+
transformer.mmdit.blocks.19.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 638 |
+
transformer.mmdit.blocks.19.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 639 |
+
transformer.mmdit.blocks.19.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 640 |
+
transformer.mmdit.blocks.19.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 641 |
+
transformer.mmdit.blocks.19.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 642 |
+
transformer.mmdit.blocks.19.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 643 |
+
transformer.mmdit.blocks.19.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 644 |
+
transformer.mmdit.blocks.19.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 645 |
+
transformer.mmdit.blocks.19.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 646 |
+
transformer.mmdit.blocks.19.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 647 |
+
transformer.mmdit.blocks.19.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 648 |
+
transformer.mmdit.blocks.19.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 649 |
+
transformer.mmdit.blocks.19.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 650 |
+
transformer.mmdit.blocks.19.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 651 |
+
transformer.mmdit.blocks.19.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 652 |
+
transformer.mmdit.blocks.19.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 653 |
+
transformer.mmdit.blocks.19.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 654 |
+
transformer.mmdit.blocks.19.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 655 |
+
transformer.mmdit.blocks.20.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 656 |
+
transformer.mmdit.blocks.20.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 657 |
+
transformer.mmdit.blocks.20.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 658 |
+
transformer.mmdit.blocks.20.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 659 |
+
transformer.mmdit.blocks.20.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 660 |
+
transformer.mmdit.blocks.20.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 661 |
+
transformer.mmdit.blocks.20.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 662 |
+
transformer.mmdit.blocks.20.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 663 |
+
transformer.mmdit.blocks.20.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 664 |
+
transformer.mmdit.blocks.20.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 665 |
+
transformer.mmdit.blocks.20.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 666 |
+
transformer.mmdit.blocks.20.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 667 |
+
transformer.mmdit.blocks.20.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 668 |
+
transformer.mmdit.blocks.20.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 669 |
+
transformer.mmdit.blocks.20.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 670 |
+
transformer.mmdit.blocks.20.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 671 |
+
transformer.mmdit.blocks.20.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 672 |
+
transformer.mmdit.blocks.20.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 673 |
+
transformer.mmdit.blocks.20.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 674 |
+
transformer.mmdit.blocks.20.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 675 |
+
transformer.mmdit.blocks.20.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 676 |
+
transformer.mmdit.blocks.20.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 677 |
+
transformer.mmdit.blocks.20.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 678 |
+
transformer.mmdit.blocks.20.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 679 |
+
transformer.mmdit.blocks.20.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 680 |
+
transformer.mmdit.blocks.20.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 681 |
+
transformer.mmdit.blocks.20.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 682 |
+
transformer.mmdit.blocks.20.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 683 |
+
transformer.mmdit.blocks.20.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 684 |
+
transformer.mmdit.blocks.20.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 685 |
+
transformer.mmdit.blocks.20.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 686 |
+
transformer.mmdit.blocks.20.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 687 |
+
transformer.mmdit.blocks.21.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 688 |
+
transformer.mmdit.blocks.21.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 689 |
+
transformer.mmdit.blocks.21.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 690 |
+
transformer.mmdit.blocks.21.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 691 |
+
transformer.mmdit.blocks.21.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 692 |
+
transformer.mmdit.blocks.21.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 693 |
+
transformer.mmdit.blocks.21.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 694 |
+
transformer.mmdit.blocks.21.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 695 |
+
transformer.mmdit.blocks.21.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 696 |
+
transformer.mmdit.blocks.21.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 697 |
+
transformer.mmdit.blocks.21.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 698 |
+
transformer.mmdit.blocks.21.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 699 |
+
transformer.mmdit.blocks.21.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 700 |
+
transformer.mmdit.blocks.21.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 701 |
+
transformer.mmdit.blocks.21.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 702 |
+
transformer.mmdit.blocks.21.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 703 |
+
transformer.mmdit.blocks.21.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 704 |
+
transformer.mmdit.blocks.21.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 705 |
+
transformer.mmdit.blocks.21.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 706 |
+
transformer.mmdit.blocks.21.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 707 |
+
transformer.mmdit.blocks.21.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 708 |
+
transformer.mmdit.blocks.21.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 709 |
+
transformer.mmdit.blocks.21.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 710 |
+
transformer.mmdit.blocks.21.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 711 |
+
transformer.mmdit.blocks.21.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 712 |
+
transformer.mmdit.blocks.21.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 713 |
+
transformer.mmdit.blocks.21.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 714 |
+
transformer.mmdit.blocks.21.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 715 |
+
transformer.mmdit.blocks.21.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 716 |
+
transformer.mmdit.blocks.21.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 717 |
+
transformer.mmdit.blocks.21.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 718 |
+
transformer.mmdit.blocks.21.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 719 |
+
transformer.mmdit.blocks.22.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 720 |
+
transformer.mmdit.blocks.22.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 721 |
+
transformer.mmdit.blocks.22.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 722 |
+
transformer.mmdit.blocks.22.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 723 |
+
transformer.mmdit.blocks.22.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 724 |
+
transformer.mmdit.blocks.22.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 725 |
+
transformer.mmdit.blocks.22.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 726 |
+
transformer.mmdit.blocks.22.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 727 |
+
transformer.mmdit.blocks.22.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 728 |
+
transformer.mmdit.blocks.22.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 729 |
+
transformer.mmdit.blocks.22.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 730 |
+
transformer.mmdit.blocks.22.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 731 |
+
transformer.mmdit.blocks.22.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 732 |
+
transformer.mmdit.blocks.22.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 733 |
+
transformer.mmdit.blocks.22.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 734 |
+
transformer.mmdit.blocks.22.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 735 |
+
transformer.mmdit.blocks.22.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 736 |
+
transformer.mmdit.blocks.22.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 737 |
+
transformer.mmdit.blocks.22.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 738 |
+
transformer.mmdit.blocks.22.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 739 |
+
transformer.mmdit.blocks.22.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 740 |
+
transformer.mmdit.blocks.22.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 741 |
+
transformer.mmdit.blocks.22.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 742 |
+
transformer.mmdit.blocks.22.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 743 |
+
transformer.mmdit.blocks.22.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 744 |
+
transformer.mmdit.blocks.22.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 745 |
+
transformer.mmdit.blocks.22.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 746 |
+
transformer.mmdit.blocks.22.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 747 |
+
transformer.mmdit.blocks.22.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 748 |
+
transformer.mmdit.blocks.22.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 749 |
+
transformer.mmdit.blocks.22.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 750 |
+
transformer.mmdit.blocks.22.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 751 |
+
transformer.mmdit.blocks.23.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 752 |
+
transformer.mmdit.blocks.23.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 753 |
+
transformer.mmdit.blocks.23.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 754 |
+
transformer.mmdit.blocks.23.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 755 |
+
transformer.mmdit.blocks.23.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 756 |
+
transformer.mmdit.blocks.23.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 757 |
+
transformer.mmdit.blocks.23.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 758 |
+
transformer.mmdit.blocks.23.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 759 |
+
transformer.mmdit.blocks.23.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 760 |
+
transformer.mmdit.blocks.23.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 761 |
+
transformer.mmdit.blocks.23.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 762 |
+
transformer.mmdit.blocks.23.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 763 |
+
transformer.mmdit.blocks.23.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 764 |
+
transformer.mmdit.blocks.23.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 765 |
+
transformer.mmdit.blocks.23.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 766 |
+
transformer.mmdit.blocks.23.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 767 |
+
transformer.mmdit.blocks.23.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 768 |
+
transformer.mmdit.blocks.23.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 769 |
+
transformer.mmdit.blocks.23.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 770 |
+
transformer.mmdit.blocks.23.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 771 |
+
transformer.mmdit.blocks.23.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 772 |
+
transformer.mmdit.blocks.23.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 773 |
+
transformer.mmdit.blocks.23.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 774 |
+
transformer.mmdit.blocks.23.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 775 |
+
transformer.mmdit.blocks.23.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 776 |
+
transformer.mmdit.blocks.23.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 777 |
+
transformer.mmdit.blocks.23.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 778 |
+
transformer.mmdit.blocks.23.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 779 |
+
transformer.mmdit.blocks.23.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 780 |
+
transformer.mmdit.blocks.23.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 781 |
+
transformer.mmdit.blocks.23.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 782 |
+
transformer.mmdit.blocks.23.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 783 |
+
transformer.mmdit.blocks.24.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 784 |
+
transformer.mmdit.blocks.24.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 785 |
+
transformer.mmdit.blocks.24.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 786 |
+
transformer.mmdit.blocks.24.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 787 |
+
transformer.mmdit.blocks.24.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 788 |
+
transformer.mmdit.blocks.24.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 789 |
+
transformer.mmdit.blocks.24.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 790 |
+
transformer.mmdit.blocks.24.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 791 |
+
transformer.mmdit.blocks.24.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 792 |
+
transformer.mmdit.blocks.24.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 793 |
+
transformer.mmdit.blocks.24.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 794 |
+
transformer.mmdit.blocks.24.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 795 |
+
transformer.mmdit.blocks.24.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 796 |
+
transformer.mmdit.blocks.24.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 797 |
+
transformer.mmdit.blocks.24.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 798 |
+
transformer.mmdit.blocks.24.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 799 |
+
transformer.mmdit.blocks.24.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 800 |
+
transformer.mmdit.blocks.24.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 801 |
+
transformer.mmdit.blocks.24.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 802 |
+
transformer.mmdit.blocks.24.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 803 |
+
transformer.mmdit.blocks.24.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 804 |
+
transformer.mmdit.blocks.24.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 805 |
+
transformer.mmdit.blocks.24.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 806 |
+
transformer.mmdit.blocks.24.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 807 |
+
transformer.mmdit.blocks.24.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 808 |
+
transformer.mmdit.blocks.24.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 809 |
+
transformer.mmdit.blocks.24.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 810 |
+
transformer.mmdit.blocks.24.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 811 |
+
transformer.mmdit.blocks.24.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 812 |
+
transformer.mmdit.blocks.24.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 813 |
+
transformer.mmdit.blocks.24.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 814 |
+
transformer.mmdit.blocks.24.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 815 |
+
transformer.mmdit.blocks.25.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 816 |
+
transformer.mmdit.blocks.25.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 817 |
+
transformer.mmdit.blocks.25.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 818 |
+
transformer.mmdit.blocks.25.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 819 |
+
transformer.mmdit.blocks.25.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 820 |
+
transformer.mmdit.blocks.25.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 821 |
+
transformer.mmdit.blocks.25.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 822 |
+
transformer.mmdit.blocks.25.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 823 |
+
transformer.mmdit.blocks.25.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 824 |
+
transformer.mmdit.blocks.25.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 825 |
+
transformer.mmdit.blocks.25.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 826 |
+
transformer.mmdit.blocks.25.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 827 |
+
transformer.mmdit.blocks.25.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 828 |
+
transformer.mmdit.blocks.25.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 829 |
+
transformer.mmdit.blocks.25.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 830 |
+
transformer.mmdit.blocks.25.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 831 |
+
transformer.mmdit.blocks.25.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 832 |
+
transformer.mmdit.blocks.25.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 833 |
+
transformer.mmdit.blocks.25.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 834 |
+
transformer.mmdit.blocks.25.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 835 |
+
transformer.mmdit.blocks.25.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 836 |
+
transformer.mmdit.blocks.25.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 837 |
+
transformer.mmdit.blocks.25.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 838 |
+
transformer.mmdit.blocks.25.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 839 |
+
transformer.mmdit.blocks.25.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 840 |
+
transformer.mmdit.blocks.25.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 841 |
+
transformer.mmdit.blocks.25.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 842 |
+
transformer.mmdit.blocks.25.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 843 |
+
transformer.mmdit.blocks.25.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 844 |
+
transformer.mmdit.blocks.25.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 845 |
+
transformer.mmdit.blocks.25.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 846 |
+
transformer.mmdit.blocks.25.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 847 |
+
transformer.mmdit.blocks.26.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 848 |
+
transformer.mmdit.blocks.26.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 849 |
+
transformer.mmdit.blocks.26.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 850 |
+
transformer.mmdit.blocks.26.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 851 |
+
transformer.mmdit.blocks.26.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 852 |
+
transformer.mmdit.blocks.26.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 853 |
+
transformer.mmdit.blocks.26.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 854 |
+
transformer.mmdit.blocks.26.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 855 |
+
transformer.mmdit.blocks.26.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 856 |
+
transformer.mmdit.blocks.26.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 857 |
+
transformer.mmdit.blocks.26.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 858 |
+
transformer.mmdit.blocks.26.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 859 |
+
transformer.mmdit.blocks.26.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 860 |
+
transformer.mmdit.blocks.26.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 861 |
+
transformer.mmdit.blocks.26.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 862 |
+
transformer.mmdit.blocks.26.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 863 |
+
transformer.mmdit.blocks.26.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 864 |
+
transformer.mmdit.blocks.26.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 865 |
+
transformer.mmdit.blocks.26.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 866 |
+
transformer.mmdit.blocks.26.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 867 |
+
transformer.mmdit.blocks.26.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 868 |
+
transformer.mmdit.blocks.26.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 869 |
+
transformer.mmdit.blocks.26.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 870 |
+
transformer.mmdit.blocks.26.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 871 |
+
transformer.mmdit.blocks.26.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 872 |
+
transformer.mmdit.blocks.26.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 873 |
+
transformer.mmdit.blocks.26.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 874 |
+
transformer.mmdit.blocks.26.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 875 |
+
transformer.mmdit.blocks.26.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 876 |
+
transformer.mmdit.blocks.26.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 877 |
+
transformer.mmdit.blocks.26.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 878 |
+
transformer.mmdit.blocks.26.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 879 |
+
transformer.mmdit.blocks.27.attn.in_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 880 |
+
transformer.mmdit.blocks.27.attn.in_projs.0.lora_B.default.weight shape=(2304x16) numel=36864
|
| 881 |
+
transformer.mmdit.blocks.27.attn.in_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 882 |
+
transformer.mmdit.blocks.27.attn.in_projs.1.lora_B.default.weight shape=(2304x16) numel=36864
|
| 883 |
+
transformer.mmdit.blocks.27.attn.in_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 884 |
+
transformer.mmdit.blocks.27.attn.in_projs.2.lora_B.default.weight shape=(2304x16) numel=36864
|
| 885 |
+
transformer.mmdit.blocks.27.attn.in_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 886 |
+
transformer.mmdit.blocks.27.attn.in_projs.3.lora_B.default.weight shape=(2304x16) numel=36864
|
| 887 |
+
transformer.mmdit.blocks.27.attn.out_projs.0.lora_A.default.weight shape=(16x768) numel=12288
|
| 888 |
+
transformer.mmdit.blocks.27.attn.out_projs.0.lora_B.default.weight shape=(768x16) numel=12288
|
| 889 |
+
transformer.mmdit.blocks.27.attn.out_projs.1.lora_A.default.weight shape=(16x768) numel=12288
|
| 890 |
+
transformer.mmdit.blocks.27.attn.out_projs.1.lora_B.default.weight shape=(768x16) numel=12288
|
| 891 |
+
transformer.mmdit.blocks.27.attn.out_projs.2.lora_A.default.weight shape=(16x768) numel=12288
|
| 892 |
+
transformer.mmdit.blocks.27.attn.out_projs.2.lora_B.default.weight shape=(768x16) numel=12288
|
| 893 |
+
transformer.mmdit.blocks.27.attn.out_projs.3.lora_A.default.weight shape=(16x768) numel=12288
|
| 894 |
+
transformer.mmdit.blocks.27.attn.out_projs.3.lora_B.default.weight shape=(768x16) numel=12288
|
| 895 |
+
transformer.mmdit.blocks.27.mlps.0.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 896 |
+
transformer.mmdit.blocks.27.mlps.0.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 897 |
+
transformer.mmdit.blocks.27.mlps.0.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 898 |
+
transformer.mmdit.blocks.27.mlps.0.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 899 |
+
transformer.mmdit.blocks.27.mlps.1.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 900 |
+
transformer.mmdit.blocks.27.mlps.1.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 901 |
+
transformer.mmdit.blocks.27.mlps.1.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 902 |
+
transformer.mmdit.blocks.27.mlps.1.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 903 |
+
transformer.mmdit.blocks.27.mlps.2.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 904 |
+
transformer.mmdit.blocks.27.mlps.2.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 905 |
+
transformer.mmdit.blocks.27.mlps.2.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 906 |
+
transformer.mmdit.blocks.27.mlps.2.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
| 907 |
+
transformer.mmdit.blocks.27.mlps.3.fc1.lora_A.default.weight shape=(16x768) numel=12288
|
| 908 |
+
transformer.mmdit.blocks.27.mlps.3.fc1.lora_B.default.weight shape=(3072x16) numel=49152
|
| 909 |
+
transformer.mmdit.blocks.27.mlps.3.fc2.lora_A.default.weight shape=(16x3072) numel=49152
|
| 910 |
+
transformer.mmdit.blocks.27.mlps.3.fc2.lora_B.default.weight shape=(768x16) numel=12288
|
mmflow-libero/libero-s1/wandb_id.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
1g1etj9b
|