Upload 23 files

model_index.json

@@ -0,0 +1,42 @@
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.30.3",
+  "_name_or_path": "SG161222/RealVisXL_V5.0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "force_zeros_for_empty_prompt": true,
+  "image_encoder": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerAncestralDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,19 @@
+{
+  "_class_name": "EulerAncestralDiscreteScheduler",
+  "_diffusers_version": "0.30.3",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/root/.cache/huggingface/hub/models--SG161222--RealVisXL_V5.0/snapshots/ac93e0dda1f6d448cae19bbfab8c5e720a5e48bc/text_encoder",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "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": "float64",
+  "transformers_version": "4.44.2",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad15f4bfdf80915d537f9a769d5ea6abc1e7fd661728abfc5ac646a84ded1b8
+size 984507088

text_encoder_2/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/root/.cache/huggingface/hub/models--SG161222--RealVisXL_V5.0/snapshots/ac93e0dda1f6d448cae19bbfab8c5e720a5e48bc/text_encoder_2",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "float64",
+  "transformers_version": "4.44.2",
+  "vocab_size": 49408
+}

text_encoder_2/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0618a13a5e150b3c26d3881bc0ac6cc79eebf7b8bae67f3ee3e2b8926b2985ea
+size 4967019392

text_encoder_2/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7304db38bc25e2acba48d61ce127146229ef5350add4f79a81ab169b6134a1
+size 590322320

text_encoder_2/model.safetensors.index.json

@@ -0,0 +1,524 @@
+{
+  "metadata": {
+    "total_size": 5557278720
+  },
+  "weight_map": {
+    "text_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
+    "text_model.embeddings.token_embedding.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.28.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.28.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.28.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.28.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.28.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.28.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.28.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.28.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.29.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.30.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.layer_norm1.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.layer_norm1.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.layer_norm2.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.layer_norm2.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "text_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "text_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "text_model.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "text_model.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "text_projection.weight": "model-00002-of-00002.safetensors"
+  }
+}

tokenizer/special_tokens_map.json

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

tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "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": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_2/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  }
+}

tokenizer_2/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "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|>"
+}

unet/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.30.3",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--SG161222--RealVisXL_V5.0/snapshots/ac93e0dda1f6d448cae19bbfab8c5e720a5e48bc/unet",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 128,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6f9a7ec5872531de6c4f39b1f8d18d064a778dad913be11dccf814eb4f8eb4
+size 9965623152

unet/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8160ac1b64c67ddd1420c8bed23f6c97632f94f7fb5b74771f20db5a6c8bcfa
+size 9905495608

unet/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78d808d417005ab8b32255743ab9c9310e4f025c95862bfed3ae51b979c6b53
+size 668813488

vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.30.3",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--SG161222--RealVisXL_V5.0/snapshots/ac93e0dda1f6d448cae19bbfab8c5e720a5e48bc/vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2626f34cce67bad0c855cd88cf6280830c2dd0c5dd384f109066505c706bc11e
+size 669258784