Upload folder using huggingface_hub

text_encoder_2/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "black-forest-labs/FLUX.1-dev",
+  "architectures": [
+    "T5EncoderModel"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

text_encoder_2/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dea06b1d7fa59f06f386c9d4844187fab1762e94d76812cf0c8325078cefb785
+size 4985367952

text_encoder_2/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b6f6464fd2a6075db2a8eb938ab92fa9096dae4390132ec96299ea840672631
+size 176360624

text_encoder_2/model.safetensors.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 5161641280
+  },
+  "weight_map": {
+    "encoder.block.0.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.input_scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.output_scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight._data": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight._scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.input_scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.output_scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight._data": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight._scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.input_scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.output_scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight._data": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight._scale": "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.input_scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.output_scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight._data": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight._scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.input_scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.output_scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight._data": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight._scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.input_scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.output_scale": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight._data": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight._scale": "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.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight._scale": "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"
+  }
+}

text_encoder_2/quanto_qmap.json

@@ -0,0 +1,674 @@
+{
+    "encoder.block.0.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.0.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.0.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.0.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.0.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.0.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.0.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.1.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.1.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.1.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.1.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.1.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.1.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.1.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.2.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.2.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.2.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.2.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.2.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.2.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.2.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.3.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.3.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.3.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.3.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.3.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.3.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.3.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.4.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.4.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.4.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.4.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.4.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.4.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.4.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.5.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.5.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.5.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.5.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.5.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.5.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.5.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.6.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.6.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.6.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.6.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.6.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.6.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.6.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.7.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.7.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.7.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.7.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.7.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.7.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.7.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.8.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.8.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.8.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.8.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.8.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.8.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.8.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.9.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.9.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.9.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.9.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.9.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.9.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.9.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.10.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.10.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.10.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.10.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.10.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.10.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.10.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.11.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.11.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.11.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.11.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.11.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.11.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.11.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.12.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.12.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.12.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.12.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.12.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.12.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.12.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.13.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.13.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.13.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.13.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.13.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.13.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.13.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.14.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.14.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.14.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.14.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.14.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.14.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.14.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.15.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.15.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.15.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.15.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.15.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.15.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.15.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.16.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.16.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.16.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.16.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.16.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.16.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.16.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.17.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.17.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.17.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.17.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.17.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.17.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.17.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.18.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.18.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.18.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.18.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.18.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.18.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.18.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.19.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.19.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.19.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.19.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.19.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.19.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.19.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.20.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.20.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.20.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.20.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.20.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.20.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.20.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.21.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.21.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.21.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.21.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.21.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.21.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.21.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.22.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.22.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.22.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.22.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.22.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.22.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.22.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.23.layer.0.SelfAttention.q": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.23.layer.0.SelfAttention.k": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.23.layer.0.SelfAttention.v": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.23.layer.0.SelfAttention.o": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.23.layer.1.DenseReluDense.wi_0": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.23.layer.1.DenseReluDense.wi_1": {
+        "weights": "qint8",
+        "activations": "none"
+    },
+    "encoder.block.23.layer.1.DenseReluDense.wo": {
+        "weights": "qint8",
+        "activations": "none"
+    }
+}