Upload folder using huggingface_hub

README.md

@@ -0,0 +1,34 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- beomi/kcbert-base
+---
+
+# TAPAS-KCBERT-slerp2
+
+TAPAS-KCBERT-slerp2 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [beomi/kcbert-base](https://huggingface.co/beomi/kcbert-base)
+* [beomi/kcbert-base](https://huggingface.co/beomi/kcbert-base)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: beomi/kcbert-base
+        layer_range: [0, 12]  # TAPAS 모델의 레이어 범위
+      - model: beomi/kcbert-base
+        layer_range: [0, 12]  # KCBERT 모델의 레이어 범위
+merge_method: slerp
+base_model: beomi/kcbert-base
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "beomi/kcbert-base",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 300,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: beomi/kcbert-base
+        layer_range: [0, 12]  # TAPAS 모델의 레이어 범위
+      - model: beomi/kcbert-base
+        layer_range: [0, 12]  # KCBERT 모델의 레이어 범위
+merge_method: slerp
+base_model: beomi/kcbert-base
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7daf5ec64f44f244be87ba9a807fa2140875be07f1e6f47cb30c8ac36c64e4
+size 264000696

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 263977056}, "weight_map": {"bert.embeddings.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.embeddings.LayerNorm.weight": "model-00001-of-00001.safetensors", "bert.embeddings.position_embeddings.weight": "model-00001-of-00001.safetensors", "bert.embeddings.token_type_embeddings.weight": "model-00001-of-00001.safetensors", "cls.predictions.decoder.weight": "model-00001-of-00001.safetensors", "bert.embeddings.word_embeddings.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.LayerNorm.weight": "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.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.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.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.0.output.LayerNorm.weight": "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.1.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.attention.output.LayerNorm.weight": "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.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.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.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.1.output.LayerNorm.weight": "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.10.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.attention.output.LayerNorm.weight": "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.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.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.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.10.output.LayerNorm.weight": "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.11.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.attention.output.LayerNorm.weight": "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.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.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.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.11.output.LayerNorm.weight": "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.2.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.attention.output.LayerNorm.weight": "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.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.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.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.2.output.LayerNorm.weight": "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.3.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.attention.output.LayerNorm.weight": "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.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.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.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.3.output.LayerNorm.weight": "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.4.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.attention.output.LayerNorm.weight": "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.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.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.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.4.output.LayerNorm.weight": "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.5.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.attention.output.LayerNorm.weight": "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.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.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.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.5.output.LayerNorm.weight": "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.6.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.attention.output.LayerNorm.weight": "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.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.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.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.6.output.LayerNorm.weight": "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.7.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.attention.output.LayerNorm.weight": "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.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.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.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.7.output.LayerNorm.weight": "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.8.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.attention.output.LayerNorm.weight": "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.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.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.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.8.output.LayerNorm.weight": "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.9.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.attention.output.LayerNorm.weight": "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.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.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.intermediate.dense.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.intermediate.dense.weight": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "bert.encoder.layer.9.output.LayerNorm.weight": "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.pooler.dense.bias": "model-00001-of-00001.safetensors", "bert.pooler.dense.weight": "model-00001-of-00001.safetensors", "cls.predictions.bias": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 300,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}