Upload folder using huggingface_hub (#7)

- Upload folder using huggingface_hub (8177288e2b060382948616d9d14c3a938e5a3739)
- Delete text_encoder_3/model-00001-of-00004.safetensors (164784c6d00fc561b750c6d4a8be9db5e9d3c237)
- Delete text_encoder_3/model-00002-of-00004.safetensors (e83a5353a4e84d7cf7d47bae5917b565d2ecdd90)
- Delete text_encoder_3/model-00003-of-00004.safetensors (a3f09ddb600fb57ed15a5a513b9f71945c11eb7b)
- Delete text_encoder_3/model-00004-of-00004.safetensors (e507a67e057ef1d8d76920a3078aca5bb7f08e34)


Co-authored-by: Sayak Paul <sayakpaul@users.noreply.huggingface.co>

.gitattributes

@@ -1,36 +1,8 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+text_encoder/model.safetensors filter=lfs diff=lfs merge=lfs -text
+text_encoder_2/model.safetensors filter=lfs diff=lfs merge=lfs -text
+text_encoder_3/model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
+text_encoder_3/model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
+transformer/diffusion_pytorch_model.safetensors filter=lfs diff=lfs merge=lfs -text
+vae/diffusion_pytorch_model.safetensors filter=lfs diff=lfs merge=lfs -text
 sd3demo.jpg filter=lfs diff=lfs merge=lfs -text
+tokenizer_3/spiece.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -130,4 +130,4 @@ Please report any issues with the model or contact us:
 * Security issues:  security@stability.ai
 * Privacy issues:  privacy@stability.ai 
 * License and general: https://stability.ai/license
-* Enterprise license: https://stability.ai/enterprise
+* Enterprise license: https://stability.ai/enterprise

model_index.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "StableDiffusion3Pipeline",
   "_diffusers_version": "0.29.0.dev0",
-  "_name_or_path": "stabilityai/stable-diffusion-3-medium",
   "scheduler": [
     "diffusers",
     "FlowMatchEulerDiscreteScheduler"

text_encoder/config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "/raid/.cache/huggingface/models--stabilityai--stable-diffusion-3-medium/snapshots/84a9ff37a0a30f7252e21daae69cfd0134198d27/text_encoder",
   "architectures": [
     "CLIPTextModelWithProjection"
   ],
@@ -19,7 +18,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
-  "torch_dtype": "float32",
-  "transformers_version": "4.41.0.dev0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

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

text_encoder_2/config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "/raid/.cache/huggingface/models--stabilityai--stable-diffusion-3-medium/snapshots/84a9ff37a0a30f7252e21daae69cfd0134198d27/text_encoder_2",
   "architectures": [
     "CLIPTextModelWithProjection"
   ],
@@ -19,7 +18,7 @@
   "num_hidden_layers": 32,
   "pad_token_id": 1,
   "projection_dim": 1280,
-  "torch_dtype": "float32",
-  "transformers_version": "4.41.0.dev0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
   "vocab_size": 49408
 }

text_encoder_2/model.safetensors

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

text_encoder_3/config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "/raid/.cache/huggingface/models--stabilityai--stable-diffusion-3-medium/snapshots/84a9ff37a0a30f7252e21daae69cfd0134198d27/text_encoder_3",
   "architectures": [
     "T5EncoderModel"
   ],
@@ -25,8 +24,8 @@
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.41.0.dev0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 32128
 }

text_encoder_3/{model-00001-of-00004.safetensors → model-00001-of-00002.safetensors}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e0e98242fed1de128a73ee6fee174aa30186c66f7d70811c8ebf67d72067f38
-size 4989319680
+oid sha256:4f2751ceeb2a96edd693e539dc5d6bba0b8d3814f49a9b3798403a0cec4b2e3d
+size 4994582104

text_encoder_3/{model-00002-of-00004.safetensors → model-00002-of-00002.safetensors}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7309a33cd1780b20e3d84b2e14585d7a64ccea45079aecc86c507e381e00ed14
-size 4999830656
+oid sha256:f63154532130422309532ff56f11945fbea8266c958e3133e8e5aef85c6293c7
+size 4530066248

text_encoder_3/model-00004-of-00004.safetensors

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

text_encoder_3/model.safetensors.index.json

@@ -1,226 +1,226 @@
 {
   "metadata": {
-    "total_size": 19049242624
+    "total_size": 9524621312
   },
   "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-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"
   }
 }

transformer/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "SD3Transformer2DModel",
   "_diffusers_version": "0.29.0.dev0",
-  "_name_or_path": "/raid/.cache/huggingface/models--stabilityai--stable-diffusion-3-medium/snapshots/84a9ff37a0a30f7252e21daae69cfd0134198d27/transformer",
   "attention_head_dim": 64,
   "caption_projection_dim": 1536,
   "in_channels": 16,

text_encoder_3/model-00003-of-00004.safetensors → transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d278bf7cb4de9957cb67d8a92dc9273f88186f0c90e0f2a3de13882217d9a95c
-size 4865612720
+oid sha256:8b0e357dd04755fbfb067c63f4a883ac1de2942dd4a3240069874a17022e5418
+size 4169981408

vae/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.29.0.dev0",
-  "_name_or_path": "/raid/.cache/huggingface/models--stabilityai--stable-diffusion-3-medium/snapshots/84a9ff37a0a30f7252e21daae69cfd0134198d27/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a7dab491193da4dc5741fad9cb6ec961f57a105686f8a618fab9faafe7a958
-size 335306212
+oid sha256:f9b67a279283625caee39d61eacb5324243848477b4eb535355eaaa8423d4e09
+size 167666654