Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

text_encoder/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "BAAI/AltDiffusion-m18",
+  "architectures": [
+    "RobertaSeriesModelWithTransformation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "has_pre_transformation": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "learn_encoder": false,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "pooler_fn": "cls",
+  "position_embedding_type": "absolute",
+  "project_dim": 1024,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_attention_mask": true,
+  "use_cache": true,
+  "vocab_size": 250002
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e397f87dcd0fcf2a9bf4ccb44a220d5157284ebc8ce69331f7dcca7b19570034
+size 2248015832

tokenizer/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

tokenizer/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f92287f0b67dee728d43623a835a7fecbd87bac23f67e988e770ad20bbaf900
+size 17098172

tokenizer/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 77,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

transformer/config.json

@@ -0,0 +1,26 @@
+{
+  "_class_name": "UVit2DModel",
+  "_diffusers_version": "0.24.0.dev0",
+  "attention_dropout": 0.0,
+  "block_num_heads": 6,
+  "block_out_channels": 384,
+  "codebook_size": 8192,
+  "cond_embed_dim": 1024,
+  "downsample": true,
+  "encoder_hidden_size": 1024,
+  "hidden_dropout": 0.0,
+  "hidden_size": 768,
+  "in_channels": 384,
+  "intermediate_size": 1408,
+  "layer_norm_eps": 1e-06,
+  "ln_elementwise_affine": true,
+  "micro_cond_embed_dim": 384,
+  "micro_cond_encode_dim": 1280,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 11,
+  "num_res_blocks": 3,
+  "sample_size": 32,
+  "upsample": true,
+  "use_bias": false,
+  "vocab_size": 8256
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df57b7164157ccc162b685ab33f4ded772eeaac9000a59674c4b6ae35556782
+size 627611680

vqvae/config.json

@@ -0,0 +1,39 @@
+{
+  "_class_name": "VQModel",
+  "_diffusers_version": "0.24.0.dev0",
+  "_name_or_path": "reza-alipour/vq-tokenizer",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    256,
+    512,
+    768
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 64,
+  "layers_per_block": 2,
+  "lookup_from_codebook": true,
+  "mid_block_add_attention": false,
+  "norm_num_groups": 32,
+  "norm_type": "group",
+  "num_vq_embeddings": 8192,
+  "out_channels": 3,
+  "sample_size": 32,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "vq_embed_dim": null
+}

vqvae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74397c70e364f52785da9d4ea66a24b0643f5681b7782b5f40520aaa603cfe9b
+size 585009980