Upload folder using huggingface_hub

log_loss.csv

@@ -0,0 +1 @@
+epoch,step,global_step,loss_total,loss_sd,loss_kd_output,loss_kd_feat,lr,lamb_sd,lamb_kd_output,lamb_kd_feat

logs/text2image-fine-tune/1717745111.570705/events.out.tfevents.1717745111.9748aac584ae.7759.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74373b7c8749a20bc236c19ab2dedbe9cc3219d5b4671ee77f3ea48aaa9c00ba
+size 2374

logs/text2image-fine-tune/1717745111.57284/hparams.yml

@@ -0,0 +1,47 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+center_crop: true
+checkpointing_steps: 5
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+lambda_kd_feat: 1.0
+lambda_kd_output: 1.0
+lambda_sd: 1.0
+learning_rate: 5.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 0
+mixed_precision: null
+non_ema_revision: null
+num_train_epochs: 0
+num_valid_images: 2
+output_dir: ./results/toy_bk_tiny
+pretrained_model_name_or_path: kmpartner/bk-test
+random_flip: true
+report_to: all
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 1234
+train_batch_size: 2
+train_data_dir: ./data/laion_aes/preprocessed_11k
+unet_config_name: bk_tiny
+unet_config_path: ./src/unet_config
+use_8bit_adam: false
+use_copy_weight_from_teacher: true
+use_ema: true
+valid_prompt: a golden vase with different flowers
+valid_steps: 5

logs/text2image-fine-tune/events.out.tfevents.1717745105.9748aac584ae.7759.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06470ca76d2530d61d2e9cc63077b60e91f5cce062a36a2ae2ff46e23982a8a9
+size 88

model_index.json

@@ -1,11 +1,7 @@
 {
-  "_class_name": "StableDiffusionControlNetPipeline",
+  "_class_name": "StableDiffusionPipeline",
   "_diffusers_version": "0.28.2",
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
-  "controlnet": [
-    "diffusers",
-    "ControlNetModel"
-  ],
+  "_name_or_path": "kmpartner/bk-test",
   "feature_extractor": [
     "transformers",
     "CLIPImageProcessor"
@@ -37,6 +33,6 @@
   ],
   "vae": [
     "diffusers",
-    "AutoencoderKL"
+    "AutoencoderTiny"
   ]
 }

safety_checker/config.json

@@ -1,5 +1,6 @@
 {
-  "_name_or_path": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/safety_checker",
+  "_commit_hash": "858c800d0667613dc2f87f859e4843a95f8120cc",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--kmpartner--bk-test/snapshots/858c800d0667613dc2f87f859e4843a95f8120cc/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],
@@ -8,21 +9,160 @@
   "model_type": "clip",
   "projection_dim": 768,
   "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
     "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
     "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
     "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
     "model_type": "clip_text_model",
-    "num_attention_heads": 12
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.27.4",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
   },
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
     "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
     "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
     "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
     "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
     "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
     "num_hidden_layers": 24,
-    "patch_size": 14
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.27.4",
+    "typical_p": 1.0,
+    "use_bfloat16": false
   }
 }

safety_checker/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
-size 1215979664
+oid sha256:11cfe53105625af8c00faac32a430626641cce686454f3c39d837f14397d858b
+size 1215981832

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/text_encoder",
+  "_name_or_path": "kmpartner/bk-test",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.27.4",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3
-size 492265168
+oid sha256:71c10601ece1342fede0300fb88db71c09ece8be491b71875d18b9799a5e6c15
+size 492265880

tokenizer/tokenizer_config.json

@@ -18,13 +18,35 @@
       "special": true
     }
   },
-  "bos_token": "<|startoftext|>",
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
-  "eos_token": "<|endoftext|>",
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "errors": "replace",
   "model_max_length": 77,
   "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--kmpartner--bk-test/snapshots/858c800d0667613dc2f87f859e4843a95f8120cc/tokenizer/special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",
-  "unk_token": "<|endoftext|>"
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

unet/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.28.2",
-  "_name_or_path": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/unet",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
@@ -11,7 +10,6 @@
   "block_out_channels": [
     320,
     640,
-    1280,
     1280
   ],
   "center_input_sample": false,
@@ -24,8 +22,7 @@
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "DownBlock2D"
+    "CrossAttnDownBlock2D"
   ],
   "downsample_padding": 1,
   "dropout": 0.0,
@@ -35,10 +32,10 @@
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 4,
-  "layers_per_block": 2,
+  "layers_per_block": 1,
   "mid_block_only_cross_attention": null,
   "mid_block_scale_factor": 1,
-  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "mid_block_type": null,
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
   "num_attention_heads": null,
@@ -58,7 +55,6 @@
   "timestep_post_act": null,
   "transformer_layers_per_block": 1,
   "up_block_types": [
-    "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d27cd69d4a0aa32105087a619f32a51bc087e133be93fe23da92f3c0bcc07d79
-size 3438167536
+oid sha256:0e7506c2f819d897010902927b8f204679374d7610e0cb45cbc37489fb007ee9
+size 1293583616

vae/config.json

@@ -1,34 +1,45 @@
 {
-  "_class_name": "AutoencoderKL",
+  "_class_name": "AutoencoderTiny",
   "_diffusers_version": "0.28.2",
-  "_name_or_path": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/vae",
-  "act_fn": "silu",
+  "_name_or_path": "madebyollin/taesd",
+  "act_fn": "relu",
   "block_out_channels": [
-    128,
-    256,
-    512,
-    512
+    64,
+    64,
+    64,
+    64
   ],
-  "down_block_types": [
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D"
+  "decoder_block_out_channels": [
+    64,
+    64,
+    64,
+    64
   ],
-  "force_upcast": true,
+  "encoder_block_out_channels": [
+    64,
+    64,
+    64,
+    64
+  ],
+  "force_upcast": false,
   "in_channels": 3,
   "latent_channels": 4,
-  "latents_mean": null,
-  "latents_std": null,
-  "layers_per_block": 2,
-  "norm_num_groups": 32,
+  "latent_magnitude": 3,
+  "latent_shift": 0.5,
+  "num_decoder_blocks": [
+    3,
+    3,
+    3,
+    1
+  ],
+  "num_encoder_blocks": [
+    1,
+    3,
+    3,
+    3
+  ],
   "out_channels": 3,
-  "sample_size": 512,
-  "scaling_factor": 0.18215,
-  "up_block_types": [
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D"
-  ]
+  "scaling_factor": 1.0,
+  "upsample_fn": "nearest",
+  "upsampling_scaling_factor": 2
 }

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d2b5932bb4151e54e694fd31ccf51fca908223c9485bd56cd0e1d83ad94c49
-size 334643268
+oid sha256:d7956d561b1efbd861ad9b03fd8f01510f9e87eddc07bdfd20837009433f6ee5
+size 9793292