Upload folder using huggingface_hub

README.md

@@ -0,0 +1,30 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- xshubhamx/legal-bert-base-uncased
+- xshubhamx/InLegalBERT
+---
+
+# legal-InLegal-merge-passthrough
+
+legal-InLegal-merge-passthrough is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [xshubhamx/legal-bert-base-uncased](https://huggingface.co/xshubhamx/legal-bert-base-uncased)
+* [xshubhamx/InLegalBERT](https://huggingface.co/xshubhamx/InLegalBERT)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: xshubhamx/legal-bert-base-uncased
+        layer_range: [0, 11]
+  - sources:
+      - model: xshubhamx/InLegalBERT
+        layer_range: [0, 11]
+merge_method: passthrough
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "xshubhamx/legal-bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_ids": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Issue",
+    "1": "Court Discourse",
+    "2": "Conclusion",
+    "3": "Precedent Analysis",
+    "4": "Section Analysis",
+    "5": "Argument by Petitioner",
+    "6": "Fact",
+    "7": "Argument by Respondent",
+    "8": "Ratio",
+    "9": "Appellant",
+    "10": "Respondent",
+    "11": "Argument by Appellant",
+    "12": "Petitioner",
+    "13": "Judge",
+    "14": "Argument by Defendant"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Appellant": 9,
+    "Argument by Appellant": 11,
+    "Argument by Defendant": 14,
+    "Argument by Petitioner": 5,
+    "Argument by Respondent": 7,
+    "Conclusion": 2,
+    "Court Discourse": 1,
+    "Fact": 6,
+    "Issue": 0,
+    "Judge": 13,
+    "Petitioner": 12,
+    "Precedent Analysis": 3,
+    "Ratio": 8,
+    "Respondent": 10,
+    "Section Analysis": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

mergekit_config.yml

@@ -0,0 +1,11 @@
+
+slices:
+  - sources:
+      - model: xshubhamx/legal-bert-base-uncased
+        layer_range: [0, 11]
+  - sources:
+      - model: xshubhamx/InLegalBERT
+        layer_range: [0, 11]
+merge_method: passthrough
+dtype: bfloat16
+

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71029e7eaab9fa03e3ed75b31b5d4636c8fab8c802252f6cc659504b03f7499e
+size 360787758

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 360744990}, "weight_map": {"classifier.weight": "model-00001-of-00001.safetensors", "classifier.bias": "model-00001-of-00001.safetensors", "bert.pooler.dense.bias": "model-00001-of-00001.safetensors", "bert.pooler.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.21.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.20.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.19.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.18.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.17.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.16.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.15.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.14.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.13.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.12.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.self.value.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.self.value.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.self.key.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.self.key.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.self.query.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.attention.self.query.weight": "model-00001-of-00001.safetensors", "bert.embeddings.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.embeddings.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.embeddings.word_embeddings.weight": "model-00001-of-00001.safetensors", "bert.embeddings.token_type_embeddings.weight": "model-00001-of-00001.safetensors", "bert.embeddings.position_embeddings.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}