Delete checkpoint/1p/18000

checkpoint/1p/18000/model_index.json

@@ -1,33 +0,0 @@
-{
-  "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.15.0.dev0",
-  "feature_extractor": [
-    "transformers",
-    "CLIPImageProcessor"
-  ],
-  "requires_safety_checker": false,
-  "safety_checker": [
-    null,
-    null
-  ],
-  "scheduler": [
-    "diffusers",
-    "DDIMScheduler"
-  ],
-  "text_encoder": [
-    "transformers",
-    "CLIPTextModel"
-  ],
-  "tokenizer": [
-    "transformers",
-    "CLIPTokenizer"
-  ],
-  "unet": [
-    "diffusers",
-    "UNet2DConditionModel"
-  ],
-  "vae": [
-    "diffusers",
-    "AutoencoderKL"
-  ]
-}

checkpoint/1p/18000/text_encoder/config.json

@@ -1,25 +0,0 @@
-{
-  "_name_or_path": "/data/gyl/sdft/experiments/dataset_p1/outputs/3000",
-  "architectures": [
-    "CLIPTextModel"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "dropout": 0.0,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_size": 1024,
-  "initializer_factor": 1.0,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 77,
-  "model_type": "clip_text_model",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 23,
-  "pad_token_id": 1,
-  "projection_dim": 512,
-  "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
-  "vocab_size": 49408
-}

checkpoint/1p/18000/text_encoder/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:099b622541a3855e2ac74a611775b32ed7a8dfa715e787d1f536ec074081c0da
-size 1361678941

checkpoint/1p/18000/tokenizer/special_tokens_map.json

@@ -1,30 +0,0 @@
-{
-  "bos_token": {
-    "content": "<|startoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "!",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}

checkpoint/1p/18000/tokenizer/tokenizer_config.json

@@ -1,38 +0,0 @@
-{
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "!",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "49406": {
-      "content": "<|startoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "49407": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<|startoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "do_lower_case": true,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "model_max_length": 77,
-  "pad_token": "!",
-  "tokenizer_class": "CLIPTokenizer",
-  "unk_token": "<|endoftext|>"
-}

checkpoint/1p/18000/unet/config.json

@@ -1,57 +0,0 @@
-{
-  "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.15.0.dev0",
-  "_name_or_path": "/data/gyl/sdft/experiments/dataset_p1/outputs/3000",
-  "act_fn": "silu",
-  "attention_head_dim": [
-    5,
-    10,
-    20,
-    20
-  ],
-  "block_out_channels": [
-    320,
-    640,
-    1280,
-    1280
-  ],
-  "center_input_sample": false,
-  "class_embed_type": null,
-  "class_embeddings_concat": false,
-  "conv_in_kernel": 3,
-  "conv_out_kernel": 3,
-  "cross_attention_dim": 1024,
-  "down_block_types": [
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "DownBlock2D"
-  ],
-  "downsample_padding": 1,
-  "dual_cross_attention": false,
-  "flip_sin_to_cos": true,
-  "freq_shift": 0,
-  "in_channels": 4,
-  "layers_per_block": 2,
-  "mid_block_scale_factor": 1,
-  "mid_block_type": "UNetMidBlock2DCrossAttn",
-  "norm_eps": 1e-05,
-  "norm_num_groups": 32,
-  "num_class_embeds": null,
-  "only_cross_attention": false,
-  "out_channels": 4,
-  "projection_class_embeddings_input_dim": null,
-  "resnet_time_scale_shift": "default",
-  "sample_size": 96,
-  "time_cond_proj_dim": null,
-  "time_embedding_type": "positional",
-  "timestep_post_act": null,
-  "up_block_types": [
-    "UpBlock2D",
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D"
-  ],
-  "upcast_attention": false,
-  "use_linear_projection": true
-}

checkpoint/1p/18000/unet/diffusion_pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7b8f2497bc091751fd2de97818435d488a6731b52cce684162e31ab444434079
-size 609972224

checkpoint/1p/18000/vae/config.json

@@ -1,31 +0,0 @@
-{
-  "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.15.0.dev0",
-  "_name_or_path": "/data/gyl/sdft/experiments/dataset_p1/outputs/3000",
-  "act_fn": "silu",
-  "block_out_channels": [
-    128,
-    256,
-    512,
-    512
-  ],
-  "down_block_types": [
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D"
-  ],
-  "in_channels": 3,
-  "latent_channels": 4,
-  "layers_per_block": 2,
-  "norm_num_groups": 32,
-  "out_channels": 3,
-  "sample_size": 768,
-  "scaling_factor": 0.18215,
-  "up_block_types": [
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D"
-  ]
-}

checkpoint/1p/18000/vae/diffusion_pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
-size 334711857