Upload 9 files

README.md

@@ -1,3 +1,38 @@
----
-license: mit
----
+---
+base_model:
+- Mihaiii/Wartortle
+- TaylorAI/bge-micro-v2
+- TaylorAI/bge-micro
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merged
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [TaylorAI/bge-micro](https://huggingface.co/TaylorAI/bge-micro) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Mihaiii/Wartortle](https://huggingface.co/Mihaiii/Wartortle)
+* [TaylorAI/bge-micro-v2](https://huggingface.co/TaylorAI/bge-micro-v2)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: Mihaiii/Wartortle
+  - model: TaylorAI/bge-micro-v2
+  - model: TaylorAI/bge-micro
+merge_method: model_stock
+base_model: TaylorAI/bge-micro
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "TaylorAI/bge-micro",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

mergekit_config.yml

@@ -0,0 +1,6 @@
+models:
+  - model: Mihaiii/Wartortle
+  - model: TaylorAI/bge-micro-v2
+  - model: TaylorAI/bge-micro
+merge_method: model_stock
+base_model: TaylorAI/bge-micro

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8e97218c2660b74bff1af2c816ee65f2d09f3741df54626a6b57060f1b5f64
+size 69565312

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 69559296}, "weight_map": {"embeddings.LayerNorm.bias": "model-00001-of-00001.safetensors", "embeddings.LayerNorm.weight": "model-00001-of-00001.safetensors", "embeddings.position_embeddings.weight": "model-00001-of-00001.safetensors", "embeddings.token_type_embeddings.weight": "model-00001-of-00001.safetensors", "embeddings.word_embeddings.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.output.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.self.key.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.self.key.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.self.query.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.self.query.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.self.value.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.self.value.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.intermediate.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.intermediate.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.output.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.output.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.self.key.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.self.key.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.self.query.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.self.query.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.self.value.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.self.value.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.intermediate.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.intermediate.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.output.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.output.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.self.key.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.self.key.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.self.query.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.self.query.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.self.value.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.self.value.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.intermediate.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.intermediate.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.output.dense.weight": "model-00001-of-00001.safetensors", "pooler.dense.bias": "model-00001-of-00001.safetensors", "pooler.dense.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "additional_special_tokens": [
+    "[PAD]",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[MASK]"
+  ],
+  "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 +1,71 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "[PAD]",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[MASK]"
+  ],
+  "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": 1000000000000000019884624838656,
+  "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]"
+}