Upload PixArtSigmaPipeline

model_index.json

@@ -1,7 +1,7 @@
 {
-  "_class_name": "PixArtAlphaPipeline",
-  "_diffusers_version": "0.28.0.dev0",
-  "_name_or_path": "test",
+  "_class_name": "PixArtSigmaPipeline",
+  "_diffusers_version": "0.29.2",
+  "_name_or_path": "frutiemax/TwistedReality-pixart-1024ms",
   "scheduler": [
     "diffusers",
     "DPMSolverMultistepScheduler"
@@ -16,7 +16,7 @@
   ],
   "transformer": [
     "diffusers",
-    "Transformer2DModel"
+    "PixArtTransformer2DModel"
   ],
   "vae": [
     "diffusers",

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "DPMSolverMultistepScheduler",
-  "_diffusers_version": "0.28.0.dev0",
+  "_diffusers_version": "0.29.2",
   "algorithm_type": "dpmsolver++",
   "beta_end": 0.02,
   "beta_schedule": "linear",

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "test/text_encoder",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--frutiemax--TwistedReality-pixart-1024ms/snapshots/3af77eec3623d60c8917ad5b58acffe4abe14a30/text_encoder",
   "architectures": [
     "T5EncoderModel"
   ],
@@ -25,8 +25,8 @@
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.36.1",
+  "torch_dtype": "float16",
+  "transformers_version": "4.42.4",
   "use_cache": true,
   "vocab_size": 32128
 }

text_encoder/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7390844be24cb8405e5c4888a0d81003ebf634af7b9ed97dc8d9122accd9d0a
+size 4994546896

text_encoder/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c247170971e3c22f5d4dba67716a132668cdd8df3019b6e605a081cc20f0464a
+size 4966239920

text_encoder/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6534420dda5ca01cad617deb236990771c5e9536fb4d771fea066c77838c86
+size 1577127552

text_encoder/model.safetensors.index.json

@@ -1,226 +1,226 @@
 {
   "metadata": {
-    "total_size": 19049242624
+    "total_size": 11537887232
   },
   "weight_map": {
-    "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.12.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.12.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.13.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.13.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.14.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.14.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.15.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.15.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.16.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.16.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.17.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.17.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.18.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
-    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.18.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.19.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.19.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.20.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.20.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.21.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.21.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.22.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.22.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.23.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.23.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
-    "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
-    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
-    "encoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
-    "encoder.final_layer_norm.weight": "model-00004-of-00004.safetensors",
-    "shared.weight": "model-00001-of-00004.safetensors"
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "shared.weight": "model-00001-of-00003.safetensors"
   }
 }

tokenizer/tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<pad>",

transformer/config.json

@@ -1,7 +1,7 @@
 {
-  "_class_name": "Transformer2DModel",
-  "_diffusers_version": "0.28.0.dev0",
-  "_name_or_path": "test/transformer",
+  "_class_name": "PixArtTransformer2DModel",
+  "_diffusers_version": "0.29.2",
+  "_name_or_path": "frutiemax/TwistedReality-pixart-1024ms",
   "activation_fn": "gelu-approximate",
   "attention_bias": true,
   "attention_head_dim": 72,

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:678b407d9183915534dc2444b83f511e12e9f5b3eb8f7a70b20a2949cc62ae1e
+oid sha256:ebb3eb1a5d2a14b289bd7ca3d8d0c87754244a7485f41f2501c29879a4d3ca6a
 size 2443492488

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.28.0.dev0",
-  "_name_or_path": "test/vae",
+  "_diffusers_version": "0.29.2",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--frutiemax--TwistedReality-pixart-1024ms/snapshots/3af77eec3623d60c8917ad5b58acffe4abe14a30/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -25,10 +25,13 @@
   "out_channels": 3,
   "sample_size": 512,
   "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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98a14dc6fe8d71c83576f135a87c61a16561c9c080abba418d2cc976ee034f88
-size 334643268
+oid sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
+size 167335342