Upload folder using huggingface_hub

.gitattributes

@@ -71,3 +71,6 @@ models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_rest
 models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4/validation_video_0_The_scene_features_a_deta.mp4 filter=lfs diff=lfs merge=lfs -text
 models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4/validation_video_0_The_video_showcases_the_S.mp4 filter=lfs diff=lfs merge=lfs -text
 models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4/validation_video_0_The_video_transports_view.mp4 filter=lfs diff=lfs merge=lfs -text
+models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/validation_video_0_2,_In_the_video,_an_elder.mp4 filter=lfs diff=lfs merge=lfs -text
+models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/validation_video_0_2,_The_video_showcases_th.mp4 filter=lfs diff=lfs merge=lfs -text
+models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/validation_video_0_2,_The_video_transports_v.mp4 filter=lfs diff=lfs merge=lfs -text

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-100/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98c9370da6970b5147d59c6b479504e456414412b68755e263d2b550befb918c
+size 3701673978

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-100/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:671cda3d1336de1afca1c2a6cf800e221ad655c0800c32791adf91f1efa861b0
+size 16036

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-100/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9682b9b65c47b86fbced2afa76caa57881592d40b28fa757a99b88e164e6c421
+size 1000

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-100/transformer/config.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "CogVideoXTransformer3DModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "THUDM/CogVideoX-5b",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 64,
+  "dropout": 0.0,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 16,
+  "max_text_seq_length": 226,
+  "norm_elementwise_affine": true,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 48,
+  "num_layers": 42,
+  "ofs_embed_dim": null,
+  "out_channels": 16,
+  "patch_bias": false,
+  "patch_size": 2,
+  "patch_size_t": 2,
+  "sample_frames": 81,
+  "sample_height": 300,
+  "sample_width": 300,
+  "spatial_interpolation_scale": 1.875,
+  "temporal_compression_ratio": 4,
+  "temporal_interpolation_scale": 1.0,
+  "text_embed_dim": 4096,
+  "time_embed_dim": 512,
+  "timestep_activation_fn": "silu",
+  "use_learned_positional_embeddings": false,
+  "use_rotary_positional_embeddings": true
+}

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-100/transformer/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09842b3e335bf14fed3d24df101dd2e95ab9276918559758a433fc8610db7184
+size 4977695424

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-100/transformer/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:551c69cc28e4a6905aeba4b32807c8e5aaad513e5ec7556043b6def69227d7af
+size 4948039832

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-100/transformer/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c1af103e253d0b4ad500c17e06b48528f85f30230bd6fa52d3e1e03c88b19d
+size 1215733728

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-200/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:018a4870bc4309addc655f6532133757c47e5d081a376a0a96254a699191823f
+size 3701676346

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-200/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9783b40e461aa92afdffd2713b6399d8efb555393d141f9db2f57bd530d457d4
+size 16100

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-200/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a87101a13a4d4eadf8f3754447f82aabf6bc82311450451fce3912f1294b8ff5
+size 1000

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-200/transformer/config.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "CogVideoXTransformer3DModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-100/transformer",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 64,
+  "dropout": 0.0,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 16,
+  "max_text_seq_length": 226,
+  "norm_elementwise_affine": true,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 48,
+  "num_layers": 42,
+  "ofs_embed_dim": null,
+  "out_channels": 16,
+  "patch_bias": false,
+  "patch_size": 2,
+  "patch_size_t": 2,
+  "sample_frames": 81,
+  "sample_height": 300,
+  "sample_width": 300,
+  "spatial_interpolation_scale": 1.875,
+  "temporal_compression_ratio": 4,
+  "temporal_interpolation_scale": 1.0,
+  "text_embed_dim": 4096,
+  "time_embed_dim": 512,
+  "timestep_activation_fn": "silu",
+  "use_learned_positional_embeddings": false,
+  "use_rotary_positional_embeddings": true
+}

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-200/transformer/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e50d30e7137d8cc5959c22bfcb672c0f5878a819c2cb725f00b0912d31640c3f
+size 4977695424

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-200/transformer/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40acaca2eb0da39891adbb52e824f7a23edaca9247b4d7ac11c359715a4595c8
+size 4948039832

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-200/transformer/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c1af103e253d0b4ad500c17e06b48528f85f30230bd6fa52d3e1e03c88b19d
+size 1215733728

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-300/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7cbd4d818305074970737c49442f4e8181fb35d07612d935a80f86ca21f1098
+size 3701676346

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-300/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aff8d8fc63591cfc2f42a47e76e702876d6dc4e9aa596104c27b736f68409979
+size 16100

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-300/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c954a41f4d1dc87f3e8600d09d3be5387ce8c7c63f4e7d7f4e680c4b360a355c
+size 1000

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-300/transformer/config.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "CogVideoXTransformer3DModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-200/transformer",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 64,
+  "dropout": 0.0,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 16,
+  "max_text_seq_length": 226,
+  "norm_elementwise_affine": true,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 48,
+  "num_layers": 42,
+  "ofs_embed_dim": null,
+  "out_channels": 16,
+  "patch_bias": false,
+  "patch_size": 2,
+  "patch_size_t": 2,
+  "sample_frames": 81,
+  "sample_height": 300,
+  "sample_width": 300,
+  "spatial_interpolation_scale": 1.875,
+  "temporal_compression_ratio": 4,
+  "temporal_interpolation_scale": 1.0,
+  "text_embed_dim": 4096,
+  "time_embed_dim": 512,
+  "timestep_activation_fn": "silu",
+  "use_learned_positional_embeddings": false,
+  "use_rotary_positional_embeddings": true
+}

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-300/transformer/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2b4e793aabb5288eb722948ed5ec8fcc3dbeda4fff0de771d7dc8544ea4599
+size 4977695424

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-300/transformer/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f836456f95b0fb37238440533f75928869671bc39848a10e9463988dfd979a
+size 4948039832

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-300/transformer/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c1af103e253d0b4ad500c17e06b48528f85f30230bd6fa52d3e1e03c88b19d
+size 1215733728

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-400/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58666193822724b7b22bac120d96684e548e9a1d959deb9739415e5e04291b9c
+size 3701676346

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-400/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c65bba830b708e73eccfe1be124578f88f55f9158c16fc5b65ac731ae19d262b
+size 16100

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-400/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31621d354e631e0704dedd0079b6885c45d6800c93c6ab43d2446e5ad9190908
+size 1000

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-400/transformer/config.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "CogVideoXTransformer3DModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-300/transformer",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 64,
+  "dropout": 0.0,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 16,
+  "max_text_seq_length": 226,
+  "norm_elementwise_affine": true,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 48,
+  "num_layers": 42,
+  "ofs_embed_dim": null,
+  "out_channels": 16,
+  "patch_bias": false,
+  "patch_size": 2,
+  "patch_size_t": 2,
+  "sample_frames": 81,
+  "sample_height": 300,
+  "sample_width": 300,
+  "spatial_interpolation_scale": 1.875,
+  "temporal_compression_ratio": 4,
+  "temporal_interpolation_scale": 1.0,
+  "text_embed_dim": 4096,
+  "time_embed_dim": 512,
+  "timestep_activation_fn": "silu",
+  "use_learned_positional_embeddings": false,
+  "use_rotary_positional_embeddings": true
+}

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-400/transformer/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e708924731d61ee4605398552fedd4e03b27844446351d0cdfd1168af5ead1e
+size 4977695424

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-400/transformer/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:711eb2f3598de4d9282305bef6ed8d578ed0e2503cfc893d6a7f3ae9849d7588
+size 4948039832

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-400/transformer/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c1af103e253d0b4ad500c17e06b48528f85f30230bd6fa52d3e1e03c88b19d
+size 1215733728

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3016e3ad877e296a6414f5defb890f7740828428862fe1294b12755aa8a9aa7
+size 3701676346

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca9175d7baeb9589c446b744502319a2df35c1f478c8218f4d1b87e7036dad5
+size 16100

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe0c60ae728628cbb5d5da94e1ac6765da1fae91e9a05d26c3f01ed96a83487
+size 1000

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-500/transformer/config.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "CogVideoXTransformer3DModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-300/transformer",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 64,
+  "dropout": 0.0,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 16,
+  "max_text_seq_length": 226,
+  "norm_elementwise_affine": true,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 48,
+  "num_layers": 42,
+  "ofs_embed_dim": null,
+  "out_channels": 16,
+  "patch_bias": false,
+  "patch_size": 2,
+  "patch_size_t": 2,
+  "sample_frames": 81,
+  "sample_height": 300,
+  "sample_width": 300,
+  "spatial_interpolation_scale": 1.875,
+  "temporal_compression_ratio": 4,
+  "temporal_interpolation_scale": 1.0,
+  "text_embed_dim": 4096,
+  "time_embed_dim": 512,
+  "timestep_activation_fn": "silu",
+  "use_learned_positional_embeddings": false,
+  "use_rotary_positional_embeddings": true
+}

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-500/transformer/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e371012a871f6ce7c2219aae1ee97c2213aa70b2cdb810167b46f9831cc5810d
+size 4977695424

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-500/transformer/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5007d85dfeeab321d085c02013b773e8d8b82c08fa0f2b04d0559d67e4c6b613
+size 4948039832

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/checkpoint-500/transformer/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c1af103e253d0b4ad500c17e06b48528f85f30230bd6fa52d3e1e03c88b19d
+size 1215733728

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/validation_video_0_2,_In_the_video,_an_elder.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f072546a8fb5eb838141b2e3851d64345a9e6a729dec91be2ce62d87291efd97
+size 2869221

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/validation_video_0_2,_The_video_showcases_th.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a79a3fbd6fd0a25cfc66d725cb29e0ea0338b888b8be6165b2ee136cfbc7a575
+size 3822894

models/cogvideox-sft__optimizer_adamw__steps_20000__lr-schedule_cosine_with_restarts__learning-rate_1e-4_1228/validation_video_0_2,_The_video_transports_v.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c2253915d300042161dd29f1b5b907bdf01daa35c4d2fc937db11f046946a0
+size 3904021