Upload folder using huggingface_hub

README.md

@@ -0,0 +1,44 @@
+---
+base_model:
+- kweinmeister/distilbert-base-uncased-mnli
+- kweinmeister/distilbert-anli
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge-slerp
+
+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 SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [kweinmeister/distilbert-base-uncased-mnli](https://huggingface.co/kweinmeister/distilbert-base-uncased-mnli)
+* [kweinmeister/distilbert-anli](https://huggingface.co/kweinmeister/distilbert-anli)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+slices:
+  - sources:
+      - model: kweinmeister/distilbert-base-uncased-mnli
+        layer_range: [0, 6]
+      - model: kweinmeister/distilbert-anli
+        layer_range: [0, 6]
+merge_method: slerp
+base_model: kweinmeister/distilbert-base-uncased-mnli
+parameters:
+  t: 0.09999999999999998
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "kweinmeister/distilbert-base-uncased-mnli",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "vocab_size": 30522
+}

mergekit_config.yml

@@ -0,0 +1,12 @@
+
+slices:
+  - sources:
+      - model: kweinmeister/distilbert-base-uncased-mnli
+        layer_range: [0, 6]
+      - model: kweinmeister/distilbert-anli
+        layer_range: [0, 6]
+merge_method: slerp
+base_model: kweinmeister/distilbert-base-uncased-mnli
+parameters:
+  t: 0.09999999999999998
+dtype: bfloat16

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5815b83d5b4429b84c00a72d9d09ca2b1b233e2ca8673f04dc5b45ca80fdfab1
+size 133924070

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 133911558}, "weight_map": {"classifier.bias": "model-00001-of-00001.safetensors", "classifier.weight": "model-00001-of-00001.safetensors", "distilbert.embeddings.LayerNorm.bias": "model-00001-of-00001.safetensors", "distilbert.embeddings.LayerNorm.weight": "model-00001-of-00001.safetensors", "distilbert.embeddings.position_embeddings.weight": "model-00001-of-00001.safetensors", "distilbert.embeddings.word_embeddings.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.attention.k_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.attention.k_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.attention.out_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.attention.out_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.attention.q_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.attention.q_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.attention.v_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.attention.v_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.ffn.lin1.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.ffn.lin1.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.ffn.lin2.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.ffn.lin2.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.output_layer_norm.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.output_layer_norm.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.sa_layer_norm.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.0.sa_layer_norm.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.attention.k_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.attention.k_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.attention.out_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.attention.out_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.attention.q_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.attention.q_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.attention.v_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.attention.v_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.ffn.lin1.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.ffn.lin1.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.ffn.lin2.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.ffn.lin2.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.output_layer_norm.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.output_layer_norm.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.sa_layer_norm.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.1.sa_layer_norm.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.attention.k_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.attention.k_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.attention.out_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.attention.out_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.attention.q_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.attention.q_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.attention.v_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.attention.v_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.ffn.lin1.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.ffn.lin1.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.ffn.lin2.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.ffn.lin2.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.output_layer_norm.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.output_layer_norm.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.sa_layer_norm.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.2.sa_layer_norm.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.attention.k_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.attention.k_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.attention.out_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.attention.out_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.attention.q_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.attention.q_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.attention.v_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.attention.v_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.ffn.lin1.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.ffn.lin1.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.ffn.lin2.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.ffn.lin2.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.output_layer_norm.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.output_layer_norm.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.sa_layer_norm.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.3.sa_layer_norm.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.attention.k_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.attention.k_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.attention.out_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.attention.out_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.attention.q_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.attention.q_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.attention.v_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.attention.v_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.ffn.lin1.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.ffn.lin1.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.ffn.lin2.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.ffn.lin2.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.output_layer_norm.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.output_layer_norm.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.sa_layer_norm.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.4.sa_layer_norm.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.attention.k_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.attention.k_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.attention.out_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.attention.out_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.attention.q_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.attention.q_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.attention.v_lin.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.attention.v_lin.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.ffn.lin1.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.ffn.lin1.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.ffn.lin2.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.ffn.lin2.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.output_layer_norm.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.output_layer_norm.weight": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.sa_layer_norm.bias": "model-00001-of-00001.safetensors", "distilbert.transformer.layer.5.sa_layer_norm.weight": "model-00001-of-00001.safetensors", "pre_classifier.bias": "model-00001-of-00001.safetensors", "pre_classifier.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 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}