Upload corrected tokenizer and fp16 variants.

model_index.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "StableDiffusion3Pipeline",
   "_diffusers_version": "0.28.0.dev0",
+  "_name_or_path": "diffusers-internal-dev/private-model",
   "scheduler": [
     "diffusers",
     "FlowMatchEulerDiscreteScheduler"

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "../checkpoints/private-model",
+  "_name_or_path": "/raid/.cache/huggingface/models--diffusers-internal-dev--private-model/snapshots/87614c14bc1da00f36dedfe6e0a82c701c44d33d/text_encoder",
   "architectures": [
     "CLIPTextModelWithProjection"
   ],
@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float16",
-  "transformers_version": "4.40.0.dev0",
+  "transformers_version": "4.39.3",
   "vocab_size": 49408
 }

text_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e183d11db0c6b6282a4d9e0abb74125edc8692393e89ed8ee5571005f35cb1
+size 247323896

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71e183d11db0c6b6282a4d9e0abb74125edc8692393e89ed8ee5571005f35cb1
-size 247323896
+oid sha256:fab2e9f2a5d3d8822ebd40a4f0ad22d5119dde950b31f8922c3e8d5622704a1c
+size 494624560

text_encoder_2/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "/raid/.cache/huggingface/models--diffusers-internal-dev--private-model/snapshots/87614c14bc1da00f36dedfe6e0a82c701c44d33d/text_encoder_2",
   "architectures": [
     "CLIPTextModelWithProjection"
   ],
@@ -19,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 1280,
   "torch_dtype": "float16",
-  "transformers_version": "4.40.0.dev0",
+  "transformers_version": "4.39.3",
   "vocab_size": 49408
 }

text_encoder_2/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
+size 1389382176

text_encoder_2/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
-size 1389382176
+oid sha256:3a6032f63d37ae02bbc74ccd6a27440578cd71701f96532229d0154f55a8d3ff
+size 2778702264

text_encoder_3/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./",
+  "_name_or_path": "/raid/.cache/huggingface/models--diffusers-internal-dev--private-model/snapshots/87614c14bc1da00f36dedfe6e0a82c701c44d33d/text_encoder_3",
   "architectures": [
     "T5EncoderModel"
   ],
@@ -26,7 +26,7 @@
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.40.0.dev0",
+  "transformers_version": "4.39.3",
   "use_cache": true,
   "vocab_size": 32128
 }

text_encoder_3/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0e98242fed1de128a73ee6fee174aa30186c66f7d70811c8ebf67d72067f38
+size 4989319680

text_encoder_3/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7309a33cd1780b20e3d84b2e14585d7a64ccea45079aecc86c507e381e00ed14
+size 4999830656

text_encoder_3/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d278bf7cb4de9957cb67d8a92dc9273f88186f0c90e0f2a3de13882217d9a95c
+size 4865612720

text_encoder_3/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69afce9a62402b82095baa1dfef572be92dfd9a4062693d49a5948e4d27585a5
+size 4194506688

text_encoder_3/model.fp16-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2806b1cf07fc6eac6c5059811aea4e069d69df34b782a0a85cd6a2b57de48404
+size 4994546896

text_encoder_3/model.fp16-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51aa7ace7b240403ef440b7387445aee7dd585cd0240d7773567cad5a0f1ed61
+size 4966239920

text_encoder_3/model.fp16-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366835891170b04927afee017584da714dfdb74aac0022d742943a46c612cae7
+size 1577127552

text_encoder_3/model.safetensors.index.fp16.json

@@ -0,0 +1,226 @@
+{
+  "metadata": {
+    "total_size": 11537887232
+  },
+  "weight_map": {
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.17.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.17.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.18.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.18.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.19.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.19.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.20.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.20.layer.1.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.1.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.1.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.1.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.6.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.7.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.8.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.9.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.final_layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "shared.weight": "model.fp16-00001-of-00003.safetensors"
+  }
+}

text_encoder_3/model.safetensors.index.json

@@ -1,226 +1,226 @@
 {
   "metadata": {
-    "total_size": 9524621312
+    "total_size": 19049242624
   },
   "weight_map": {
-    "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
-    "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
-    "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
-    "encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "shared.weight": "model-00001-of-00002.safetensors"
+    "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"
   }
 }

tokenizer_2/special_tokens_map.json

@@ -13,13 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "!",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_2/tokenizer_config.json

@@ -24,7 +24,7 @@
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 77,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "!",
   "tokenizer_class": "CLIPTokenizer",
   "unk_token": "<|endoftext|>"
 }

transformer/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "SD3Transformer2DModel",
   "_diffusers_version": "0.28.0.dev0",
-  "_name_or_path": "diffusers/diffusers_sd3",
+  "_name_or_path": "/raid/.cache/huggingface/models--diffusers-internal-dev--private-model/snapshots/87614c14bc1da00f36dedfe6e0a82c701c44d33d/transformer",
   "attention_head_dim": 64,
   "caption_projection_dim": 1152,
   "cross_attention_dim": 4096,

transformer/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b117e1b8ce784edcfbabba0850209ee1fc72f06fb97246bc6d0ee61b140bf1
+size 1733611920

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.28.0.dev0",
-  "_name_or_path": "../sdxl-vae/",
+  "_name_or_path": "/raid/.cache/huggingface/models--diffusers-internal-dev--private-model/snapshots/87614c14bc1da00f36dedfe6e0a82c701c44d33d/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,

vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1173613744f03c3c49b15fbf4a33829736931e1217aca4b1b11d2057a4581fd
+size 167666654

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1173613744f03c3c49b15fbf4a33829736931e1217aca4b1b11d2057a4581fd
-size 167666654
+oid sha256:d972e5c4aa354ca9eeee7517bd8b6a7da1c2df2cdf8d657723f689ca1ad65679
+size 335306212