add model

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "openMUSE/clip-vit-large-patch14-text-enc",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95397de1a082dd0f90f1a7c93b1aaf8408c11d41d11f2a7dbdd4c32595b59bb3
+size 247368805

text_encoder/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

text_encoder/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "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": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

transformer/config.json

@@ -0,0 +1,54 @@
+{
+  "_class_name": "MaskGiTUViT",
+  "_name_or_path": "./hf-model/muse-research-run/ema_model/",
+  "_version": "0.0.1",
+  "add_cond_embeds": true,
+  "add_cross_attention": true,
+  "add_micro_cond_embeds": true,
+  "attention_dropout": 0.0,
+  "block_has_attention": [
+    true
+  ],
+  "block_num_heads": [
+    12
+  ],
+  "block_out_channels": [
+    768
+  ],
+  "codebook_size": 8192,
+  "cond_embed_dim": 768,
+  "encoder_hidden_size": 768,
+  "ffn_type": "glu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "in_channels": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "layer_norm_before_mlm": false,
+  "layer_norm_embedddings": false,
+  "layer_norm_eps": 1e-06,
+  "learn_uncond_embeds": false,
+  "ln_elementwise_affine": true,
+  "mask_token_id": 8255,
+  "max_position_embeddings": 256,
+  "micro_cond_embed_dim": 1280,
+  "micro_cond_encode_dim": 256,
+  "norm_type": "rmsnorm",
+  "num_attention_heads": 16,
+  "num_classes": null,
+  "num_hidden_layers": 22,
+  "num_res_blocks": 3,
+  "num_vq_tokens": 256,
+  "patch_size": 1,
+  "project_encoder_hidden_states": true,
+  "res_ffn_factor": 4,
+  "use_bias": false,
+  "use_codebook_size_for_output": true,
+  "use_empty_embeds_for_uncond": true,
+  "use_encoder_layernorm": false,
+  "use_normformer": false,
+  "use_position_embeddings": false,
+  "use_vannilla_resblock": false,
+  "vocab_size": 8256,
+  "xavier_init_embed": true
+}

transformer/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd8a95d9f0f7851a200ccf22200d0db6942843972f8f7a975fa1e8468bb04a8
+size 1207296845

vae/config.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "VQGANModel",
+  "_name_or_path": "openMUSE/vqgan-f16-8192-laion",
+  "_version": "0.0.1",
+  "attn_resolutions": [],
+  "channel_mult": [
+    1,
+    2,
+    2,
+    4,
+    6
+  ],
+  "commitment_cost": 0.25,
+  "dropout": 0.0,
+  "hidden_channels": 128,
+  "no_attn_mid_block": true,
+  "num_channels": 3,
+  "num_embeddings": 8192,
+  "num_res_blocks": 2,
+  "quantized_embed_dim": 64,
+  "resample_with_conv": true,
+  "resolution": 256,
+  "z_channels": 64
+}

vae/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c64762c56326dcd7de00706cc12e739327961ea9cf0de4913fa5b638e876793
+size 585081633