Upload folder using huggingface_hub

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "retrieva-jp/bert-1.3b",
+  "architectures": [
+    "RetrievaBertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoConfig": "retrieva-jp/bert-1.3b--configuration_retrieva_bert.RetrievaBertConfig",
+    "AutoModel": "retrieva-jp/bert-1.3b--modeling_retrieva_bert.RetrievaBertModel",
+    "AutoModelForCausalLM": "retrieva-jp/bert-1.3b--modeling_retrieva_bert.RetrievaBertForCausalLM",
+    "AutoModelForMaskedLM": "retrieva-jp/bert-1.3b--modeling_retrieva_bert.RetrievaBertForMaskedLM",
+    "AutoModelForMultipleChoice": "retrieva-jp/bert-1.3b--modeling_retrieva_bert.RetrievaBertForMultipleChoice",
+    "AutoModelForNextSentencePrediction": "retrieva-jp/bert-1.3b--modeling_retrieva_bert.RetrievaBertForNextSentencePrediction",
+    "AutoModelForPreTraining": "retrieva-jp/bert-1.3b--modeling_retrieva_bert.RetrievaBertForPreTraining",
+    "AutoModelForQuestionAnswering": "retrieva-jp/bert-1.3b--modeling_retrieva_bert.RetrievaBertForQuestionAnswering",
+    "AutoModelForSequenceClassification": "retrieva-jp/bert-1.3b--modeling_retrieva_bert.RetrievaBertForSequenceClassification",
+    "AutoModelForTokenClassification": "retrieva-jp/bert-1.3b--modeling_retrieva_bert.RetrievaBertForTokenClassification"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "lm_head_hidden_act": "gelu",
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "mlp_bias": true,
+  "model_type": "retrieva-bert",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 1,
+  "pad_token_id": 4,
+  "position_embedding_type": "absolute",
+  "rope_theta": 10000.0,
+  "rotary_percent": 1.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 0,
+  "use_cache": true,
+  "vocab_size": 99584
+}

mlp_layer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a08b46c5ac077c2428cebac0775d837f5e513fdee45ed294de91a9936afba84
+size 5214942678

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc0f8dbff597ed5e9cc5f042e016d5682f7aa62dabc3cbc5f35ddc3e9d668462
+size 4980138856

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ddf2d191918dff10d9394c108846423e91d07840f303c4ad8a061f6f067c5e
+size 225101296

model.safetensors.index.json

@@ -0,0 +1,877 @@
+{
+  "metadata": {
+    "total_size": 5205141504
+  },
+  "weight_map": {
+    "embeddings.position_embeddings.weight": "model-00001-of-00002.safetensors",
+    "embeddings.word_embeddings.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.0.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.1.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.10.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.11.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.12.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.13.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.14.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.15.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.16.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.17.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.18.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.19.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.2.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.20.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.21.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.22.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.23.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.24.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.25.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.26.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.27.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.28.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.29.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.3.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.30.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.31.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.32.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.33.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.34.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.35.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.36.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.37.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.38.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.39.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.4.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.40.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.41.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.42.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.43.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.44.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.45.output.dense.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.45.output.dense.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.attention.ln.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.attention.ln.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.intermediate.gate_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.intermediate.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.intermediate.up_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.intermediate.up_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.ln.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.ln.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.output.dense.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.46.output.dense.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.attention.ln.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.attention.ln.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.intermediate.gate_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.intermediate.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.intermediate.up_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.intermediate.up_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.ln.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.ln.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.output.dense.bias": "model-00002-of-00002.safetensors",
+    "encoder.layer.47.output.dense.weight": "model-00002-of-00002.safetensors",
+    "encoder.layer.5.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.5.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.6.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.7.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.8.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.attention.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.attention.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.attention.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.attention.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.attention.self.key.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.attention.self.key.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.attention.self.query.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.attention.self.query.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.attention.self.value.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.attention.self.value.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.intermediate.gate_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.intermediate.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.intermediate.up_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.intermediate.up_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.ln.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.ln.weight": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.output.dense.bias": "model-00001-of-00002.safetensors",
+    "encoder.layer.9.output.dense.weight": "model-00001-of-00002.safetensors",
+    "encoder.ln.bias": "model-00002-of-00002.safetensors",
+    "encoder.ln.weight": "model-00002-of-00002.safetensors",
+    "pooler.dense.bias": "model-00002-of-00002.safetensors",
+    "pooler.dense.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,54 @@
+{
+  "additional_special_tokens": [
+    "<EOD|LLM-jp>"
+  ],
+  "bos_token": {
+    "content": "<s|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<CLS|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<MASK|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<SEP|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<MASK|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<PAD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<EOD|LLM-jp>"
+  ],
+  "bos_token": "<s|LLM-jp>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "</s|LLM-jp>",
+  "eos_token": "</s|LLM-jp>",
+  "extra_ids": 0,
+  "mask_token": "<MASK|LLM-jp>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk|LLM-jp>"
+}