Upload folder using huggingface_hub

weights/flan_ul2_encoder/added_tokens.json

@@ -0,0 +1,30 @@
+{
+  "[new_id_0]": 32100,
+  "[new_id_10]": 32110,
+  "[new_id_11]": 32111,
+  "[new_id_12]": 32112,
+  "[new_id_13]": 32113,
+  "[new_id_14]": 32114,
+  "[new_id_15]": 32115,
+  "[new_id_16]": 32116,
+  "[new_id_17]": 32117,
+  "[new_id_18]": 32118,
+  "[new_id_19]": 32119,
+  "[new_id_1]": 32101,
+  "[new_id_20]": 32120,
+  "[new_id_21]": 32121,
+  "[new_id_22]": 32122,
+  "[new_id_23]": 32123,
+  "[new_id_24]": 32124,
+  "[new_id_25]": 32125,
+  "[new_id_26]": 32126,
+  "[new_id_27]": 32127,
+  "[new_id_2]": 32102,
+  "[new_id_3]": 32103,
+  "[new_id_4]": 32104,
+  "[new_id_5]": 32105,
+  "[new_id_6]": 32106,
+  "[new_id_7]": 32107,
+  "[new_id_8]": 32108,
+  "[new_id_9]": 32109
+}

weights/flan_ul2_encoder/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/home/jovyan/vladimir/imagen/kandinsky3/pretrained_encoders/flan_ul2/",
+  "architectures": [
+    "T5EncoderModel"
+  ],
+  "d_ff": 16384,
+  "d_kv": 256,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "silu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-silu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 32,
+  "num_heads": 16,
+  "num_layers": 32,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

weights/flan_ul2_encoder/projection.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ddf609d667d8364e934d7d631f71c0022d73a12567b8ea2deef14069d29d28b
+size 67142898

weights/flan_ul2_encoder/projection_flash.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e5c908fb0b6a8b0a7c6f5fbe52b72e1c31436e337d45f4538fa037973f0064b
+size 67143507

weights/flan_ul2_encoder/projection_inpainting.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b790f73c133ca9f74c04e442e4ec58c6a8f40972ed2ba6adff7fe1bf74bc4f
+size 67143478

weights/flan_ul2_encoder/pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6e2b587b61b1e17fd25fd3557cd9884101aedc97689eb6f9e7ee617d8b81b2
+size 9921935117

weights/flan_ul2_encoder/pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae08601c27e6093d272173ea8f22204562ee48f8ae35c4059d1ce2ed054373c5
+size 9999561499

weights/flan_ul2_encoder/pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd1f4ef868d66ab00c3834c5a1cb83a28a9f85a8923d8674dc3468a4d067113
+size 9865344157

weights/flan_ul2_encoder/pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f67654093fbc4df1ea2f240c910fdcf3eb54e7120f5b7cf1129ea87e6d616519
+size 5100451697

weights/flan_ul2_encoder/pytorch_model.bin.index.json

@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_size": 34887190528
+  },
+  "weight_map": {
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.24.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.24.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.24.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.24.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.24.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.24.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.24.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.25.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.25.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.25.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.25.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.25.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.25.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.25.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.26.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.26.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.26.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.26.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.26.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.26.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.26.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.27.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.27.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.27.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.27.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.27.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.27.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.27.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.28.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.28.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.28.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.28.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.28.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.28.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.28.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.29.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.29.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.29.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.29.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.29.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.29.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.29.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.30.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.30.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.30.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.30.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.30.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.30.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.30.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.31.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.31.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.31.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.31.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.31.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.31.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.31.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "shared.weight": "pytorch_model-00001-of-00004.bin"
+  }
+}

weights/flan_ul2_encoder/special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

weights/flan_ul2_encoder/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

weights/flan_ul2_encoder/tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}