up

text_encoder/config.json

@@ -1,23 +1,36 @@
 {
+  "_name_or_path": "./text_encoder/",
   "architectures": [
-    "CLIPTextModel"
+    "T5EncoderModel"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 32,
+  "dense_act_fn": "relu",
   "dropout": 0.0,
+  "dropout_rate": 0.1,
   "eos_token_id": 2,
+  "feed_forward_proj": "relu",
   "hidden_act": "quick_gelu",
-  "hidden_size": 32,
   "initializer_factor": 1.0,
   "initializer_range": 0.02,
   "intermediate_size": 37,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
   "layer_norm_eps": 1e-05,
+  "layer_norm_epsilon": 1e-06,
   "max_position_embeddings": 77,
-  "model_type": "clip_text_model",
-  "num_attention_heads": 4,
-  "num_hidden_layers": 5,
+  "model_type": "t5",
+  "num_decoder_layers": 6,
+  "num_heads": 4,
+  "num_layers": 5,
   "pad_token_id": 1,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
-  "transformers_version": "4.20.0.dev0",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
   "vocab_size": 1000
 }

text_encoder/model.safetensors.index.json

@@ -0,0 +1,50 @@
+{
+  "metadata": {
+    "total_size": 3406720
+  },
+  "weight_map": {
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00003-of-00023.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00004-of-00023.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00003-of-00023.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00023.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00003-of-00023.safetensors",
+    "encoder.block.0.layer.0.layer_norm.weight": "model-00004-of-00023.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi.weight": "model-00005-of-00023.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00006-of-00023.safetensors",
+    "encoder.block.0.layer.1.layer_norm.weight": "model-00007-of-00023.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00007-of-00023.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00008-of-00023.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00007-of-00023.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00007-of-00023.safetensors",
+    "encoder.block.1.layer.0.layer_norm.weight": "model-00008-of-00023.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi.weight": "model-00009-of-00023.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00010-of-00023.safetensors",
+    "encoder.block.1.layer.1.layer_norm.weight": "model-00011-of-00023.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00011-of-00023.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00012-of-00023.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00011-of-00023.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00011-of-00023.safetensors",
+    "encoder.block.2.layer.0.layer_norm.weight": "model-00012-of-00023.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi.weight": "model-00013-of-00023.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00014-of-00023.safetensors",
+    "encoder.block.2.layer.1.layer_norm.weight": "model-00015-of-00023.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00015-of-00023.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00016-of-00023.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00015-of-00023.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00015-of-00023.safetensors",
+    "encoder.block.3.layer.0.layer_norm.weight": "model-00016-of-00023.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi.weight": "model-00017-of-00023.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00018-of-00023.safetensors",
+    "encoder.block.3.layer.1.layer_norm.weight": "model-00019-of-00023.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00019-of-00023.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00020-of-00023.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00019-of-00023.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00019-of-00023.safetensors",
+    "encoder.block.4.layer.0.layer_norm.weight": "model-00020-of-00023.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi.weight": "model-00021-of-00023.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00022-of-00023.safetensors",
+    "encoder.block.4.layer.1.layer_norm.weight": "model-00023-of-00023.safetensors",
+    "encoder.final_layer_norm.weight": "model-00023-of-00023.safetensors",
+    "shared.weight": "model-00002-of-00023.safetensors"
+  }
+}

text_encoder/pytorch_model-00001-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be6a45202f9ac05db7838d5c383d550bd6a79229feba0107d529ed6f95039b6d
+size 537

text_encoder/pytorch_model-00002-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12353b628d2acab6c5e77aba69e9ddd7a0a614c2f0dd43fa90eb89b143e9d16d
+size 128938

text_encoder/pytorch_model-00003-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b23d5f59be191335b5e4e3fb003bc27b882e11a3c81bcebaf40cf0a17a72407
+size 128938

text_encoder/pytorch_model-00004-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a2787c0b40be163635a5337dbd759fbea1ee3583ff419b9f4a04a1be5423fd
+size 99916

text_encoder/pytorch_model-00005-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be2c2603dac2f86cb07ede81d28cb3c925ef9ac9ff02d02ca955972580b544b
+size 35020

text_encoder/pytorch_model-00006-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cadfac22c0c28c3218ef4573ba2db0d31e67d02d1f1a212b38f6d920f1797f57
+size 263082

text_encoder/pytorch_model-00007-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a6e202bd6ee304226b6bae016ece925e30200a4ad105dea1dc098dda2e3e75
+size 263082

text_encoder/pytorch_model-00008-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b561aada58bb98287a95ebb726e059c3e4fd566629e225904c60cfc568f690a0
+size 100317

text_encoder/pytorch_model-00009-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d727300dbb9536730f5be3de03c00c5bde907e1e77d44ff81c76973b56f192
+size 34171

text_encoder/pytorch_model-00010-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377054c3b9a9a29673d0116a08c4b8ac7c8f87eb58af3a4c07cc9f43183717ce
+size 263082

text_encoder/pytorch_model-00011-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206e02819496e0074f64240832608941fb3a51c68062a88f089e144fbf45e61e
+size 263082

text_encoder/pytorch_model-00012-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16eb3b4c043fca2adc8f1afc8b606427ae5ff5ba4d9885e94bd7087e6b54330a
+size 100317

text_encoder/pytorch_model-00013-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4e37992e261a7d8a605ff12cc3949837009735b982d498883e483d4baf002c
+size 34171

text_encoder/pytorch_model-00014-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c171f1826f034ebfab439ee25edd8b0c334d5ea1aec6182c9234e697bdefdd
+size 263082

text_encoder/pytorch_model-00015-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2746b8b8c718b9d2d0662cef2e83def762d60bcb7d67809276c29e861d8f6968
+size 263082

text_encoder/pytorch_model-00016-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8440ccacbc457f37fbc21ebc3e7ca4b8339e3442cf68de83b28e0548f03bc12c
+size 100317

text_encoder/pytorch_model-00017-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d72914dcf6255f59541a388ba3fda4d2887b20c0e7358b8eaf14b9f74117b3
+size 34171

text_encoder/pytorch_model-00018-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1793252508c4502732b82f92cdbb6786967d9384201b45674a5c898fe70f7f9
+size 263082

text_encoder/pytorch_model-00019-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d96339969907ad3b91f9d85c955ce80bac87526f8ce43d37ceebb5282ac366
+size 263082

text_encoder/pytorch_model-00020-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576ac52f24e8b22f456ea5f8d996af3082d4107d60d714b4615adb1496890122
+size 100317

text_encoder/pytorch_model-00021-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2b3e442c19cb73ebe91a5427936ab315191fc2732ed8494dd60508aaf2db48
+size 34171

text_encoder/pytorch_model-00022-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd63880a05eab7c7fe71ae7ce80503027fa4a2f9b6c660d487d45141ff20ce97
+size 263082

text_encoder/pytorch_model-00023-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2a2c52e70d277497370b5e242c7e5f8bff65db7585bc71d753ddd0dca4031c
+size 263082

text_encoder/pytorch_model-00024-of-00024.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bbab091d0b7ceecb2edb47d1c30617a46ec5366d3e6147c96c27e2540b37dd9
+size 1467

text_encoder/pytorch_model.bin.index.json

@@ -0,0 +1,51 @@
+{
+  "metadata": {
+    "total_size": 3534720
+  },
+  "weight_map": {
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00024.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00024.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00024.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00005-of-00024.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00024.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00005-of-00024.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model-00006-of-00024.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00024.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00008-of-00024.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00024.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00009-of-00024.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00024.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00024.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00009-of-00024.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model-00010-of-00024.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00011-of-00024.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00012-of-00024.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00012-of-00024.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00013-of-00024.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00012-of-00024.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00012-of-00024.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00013-of-00024.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model-00014-of-00024.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00015-of-00024.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00016-of-00024.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00016-of-00024.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00017-of-00024.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00016-of-00024.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00016-of-00024.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00017-of-00024.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model-00018-of-00024.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00019-of-00024.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00020-of-00024.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00020-of-00024.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00021-of-00024.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00020-of-00024.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00020-of-00024.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00021-of-00024.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model-00022-of-00024.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00023-of-00024.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00024-of-00024.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00003-of-00024.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00024-of-00024.bin",
+    "shared.weight": "pytorch_model-00002-of-00024.bin"
+  }
+}