Delete Junk Files (#4)
Browse files- Delete Junk Files (94ca250a658e1ae8d4da50224d0a1f87bc52af11)
Co-authored-by: 🎬cinema_anon <[email protected]>
- .ipynb_checkpoints/model_index-checkpoint.json +0 -32
- scheduler/.ipynb_checkpoints/scheduler_config-checkpoint.json +0 -6
- text_encoder/.ipynb_checkpoints/config-checkpoint.json +0 -61
- tokenizer/.ipynb_checkpoints/tokenizer-checkpoint.json +0 -0
- tokenizer_2/.ipynb_checkpoints/merges-checkpoint.txt +0 -0
- transformer/.ipynb_checkpoints/config-checkpoint.json +0 -37
.ipynb_checkpoints/model_index-checkpoint.json
DELETED
|
@@ -1,32 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_class_name": "Kandinsky5T2VPipeline",
|
| 3 |
-
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
-
"scheduler": [
|
| 5 |
-
"diffusers",
|
| 6 |
-
"FlowMatchEulerDiscreteScheduler"
|
| 7 |
-
],
|
| 8 |
-
"text_encoder": [
|
| 9 |
-
"transformers",
|
| 10 |
-
"Qwen2_5_VLForConditionalGeneration"
|
| 11 |
-
],
|
| 12 |
-
"tokenizer": [
|
| 13 |
-
"transformers",
|
| 14 |
-
"Qwen2VLProcessor"
|
| 15 |
-
],
|
| 16 |
-
"text_encoder_2": [
|
| 17 |
-
"transformers",
|
| 18 |
-
"CLIPTextModel"
|
| 19 |
-
],
|
| 20 |
-
"tokenizer_2": [
|
| 21 |
-
"transformers",
|
| 22 |
-
"CLIPTokenizer"
|
| 23 |
-
],
|
| 24 |
-
"transformer": [
|
| 25 |
-
"diffusers",
|
| 26 |
-
"Kandinsky5Transformer3DModel"
|
| 27 |
-
],
|
| 28 |
-
"vae": [
|
| 29 |
-
"diffusers",
|
| 30 |
-
"AutoencoderKLHunyuanVideo"
|
| 31 |
-
]
|
| 32 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
scheduler/.ipynb_checkpoints/scheduler_config-checkpoint.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 3 |
-
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
-
"num_train_timesteps": 1000,
|
| 5 |
-
"shift": 5.0
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
text_encoder/.ipynb_checkpoints/config-checkpoint.json
DELETED
|
@@ -1,61 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
-
],
|
| 5 |
-
"attention_dropout": 0.0,
|
| 6 |
-
"bos_token_id": 151643,
|
| 7 |
-
"eos_token_id": 151645,
|
| 8 |
-
"vision_start_token_id": 151652,
|
| 9 |
-
"vision_end_token_id": 151653,
|
| 10 |
-
"vision_token_id": 151654,
|
| 11 |
-
"image_token_id": 151655,
|
| 12 |
-
"video_token_id": 151656,
|
| 13 |
-
"hidden_act": "silu",
|
| 14 |
-
"hidden_size": 3584,
|
| 15 |
-
"initializer_range": 0.02,
|
| 16 |
-
"intermediate_size": 18944,
|
| 17 |
-
"max_position_embeddings": 128000,
|
| 18 |
-
"max_window_layers": 28,
|
| 19 |
-
"model_type": "qwen2_5_vl",
|
| 20 |
-
"num_attention_heads": 28,
|
| 21 |
-
"num_hidden_layers": 28,
|
| 22 |
-
"num_key_value_heads": 4,
|
| 23 |
-
"rms_norm_eps": 1e-06,
|
| 24 |
-
"rope_theta": 1000000.0,
|
| 25 |
-
"sliding_window": 32768,
|
| 26 |
-
"tie_word_embeddings": false,
|
| 27 |
-
"torch_dtype": "bfloat16",
|
| 28 |
-
"transformers_version": "4.41.2",
|
| 29 |
-
"use_cache": true,
|
| 30 |
-
"use_sliding_window": false,
|
| 31 |
-
"vision_config": {
|
| 32 |
-
"depth": 32,
|
| 33 |
-
"hidden_act": "silu",
|
| 34 |
-
"hidden_size": 1280,
|
| 35 |
-
"intermediate_size": 3420,
|
| 36 |
-
"num_heads": 16,
|
| 37 |
-
"in_chans": 3,
|
| 38 |
-
"out_hidden_size": 3584,
|
| 39 |
-
"patch_size": 14,
|
| 40 |
-
"spatial_merge_size": 2,
|
| 41 |
-
"spatial_patch_size": 14,
|
| 42 |
-
"window_size": 112,
|
| 43 |
-
"fullatt_block_indexes": [
|
| 44 |
-
7,
|
| 45 |
-
15,
|
| 46 |
-
23,
|
| 47 |
-
31
|
| 48 |
-
],
|
| 49 |
-
"tokens_per_second": 2,
|
| 50 |
-
"temporal_patch_size": 2
|
| 51 |
-
},
|
| 52 |
-
"rope_scaling": {
|
| 53 |
-
"type": "mrope",
|
| 54 |
-
"mrope_section": [
|
| 55 |
-
16,
|
| 56 |
-
24,
|
| 57 |
-
24
|
| 58 |
-
]
|
| 59 |
-
},
|
| 60 |
-
"vocab_size": 152064
|
| 61 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/.ipynb_checkpoints/tokenizer-checkpoint.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_2/.ipynb_checkpoints/merges-checkpoint.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
transformer/.ipynb_checkpoints/config-checkpoint.json
DELETED
|
@@ -1,37 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_class_name": "Kandinsky5Transformer3DModel",
|
| 3 |
-
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
-
"in_visual_dim": 16,
|
| 5 |
-
"out_visual_dim": 16,
|
| 6 |
-
"time_dim": 512,
|
| 7 |
-
"patch_size": [
|
| 8 |
-
1,
|
| 9 |
-
2,
|
| 10 |
-
2
|
| 11 |
-
],
|
| 12 |
-
"model_dim": 1792,
|
| 13 |
-
"ff_dim": 7168,
|
| 14 |
-
"num_text_blocks": 2,
|
| 15 |
-
"num_visual_blocks": 32,
|
| 16 |
-
"axes_dims": [
|
| 17 |
-
16,
|
| 18 |
-
24,
|
| 19 |
-
24
|
| 20 |
-
],
|
| 21 |
-
"visual_cond": true,
|
| 22 |
-
"in_text_dim": 3584,
|
| 23 |
-
"in_text_dim2": 768,
|
| 24 |
-
"attention_type": "nabla",
|
| 25 |
-
"attention_causal": false,
|
| 26 |
-
"attention_local": false,
|
| 27 |
-
"attention_glob": false,
|
| 28 |
-
"attention_window": 3,
|
| 29 |
-
"attention_P": 0.9,
|
| 30 |
-
"attention_wT": 11,
|
| 31 |
-
"attention_wW": 3,
|
| 32 |
-
"attention_wH": 3,
|
| 33 |
-
"attention_add_sta": true,
|
| 34 |
-
"attention_method": "topcdf"
|
| 35 |
-
}
|
| 36 |
-
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|