commit files to HF hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,17 @@
+
+# career-path-representation-mpnet-decorte
+This is a fine-tuned version of [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) on custom data.
+For fine-tuning details, preprocessing code, and how to use this model for career path prediction, visit our GitHub repository: https://github.com/elenasenger/karrierewege
+
+## Model Details
+- **Base Model**: `sentence-transformers/all-mpnet-base-v2`
+- **Fine-tuned on**: TechWolf/anonymous-working-histories
+- **Tasks**: Sentence Embeddings / Text Similarity
+- **License**: Apache-2.0
+
+## Usage
+```python
+from transformers import AutoModel, AutoTokenizer
+
+model = AutoModel.from_pretrained("ElenaSenger/career-path-representation-mpnet-decorte")
+tokenizer = AutoTokenizer.from_pretrained("ElenaSenger/career-path-representation-mpnet-decorte")

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "vocab_size": 30527
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.6.1",
+    "pytorch": "1.8.1"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

linear_transform_errors.json

@@ -0,0 +1 @@
+{"MSE": 0.613, "RMSE": 0.783}

matrix_T.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0ded96de5a4928aad925bdde98d88b9f18928cc0a51fde9f3f1f5d1c0f18fb0
+size 2359424

matrix_T_cross_cp.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e13f2e441410317e6736b8584ea4facea53c49aaeadb45b792695ca81fa6782
+size 2359424

matrix_T_cross_free.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9d7ccbde071c60fce95696b0bf79a18d6404bc9fffd5c28077d2802b934476
+size 2359424

matrix_T_decorte_esco.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abbfabec2b5033d2213a4e42c6043a9f677568baac4d068ca0a09713068849ef
+size 2359424

matrix_T_mix.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ac958ebb763abd7350e173a6a4907afc0116bbe65e0e333df79d07e2ca8136
+size 2359424

matrix_T_n.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dd3e8db9e20264796c68f49cc8620ee7c97d1f58cb3c2fb0d7685467f3f2a50
+size 2359424

matrix_T_og.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05738d9b9e8beaff910e07db013b9f6f5b954a13d3ba2e2bee7cc53c42716b9
+size 2359424

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a611c6b1baa570a5ee9f4c67d409a8807f4c5356a07da279d395df6a5177b6b
+size 437967672

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bdb5c3a20e5bdb5d49904ef5d9076d78e66c8ccdbfd4bd0f4f8a8a7da8490c6
+size 871331770

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db3b6643d353deb78f7705d28f5fb6445befdbf88cd99db6a10d3174e85dbf63
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5838385ea397312bd6503633b8c298600b010ebd84c29fcb8c232b5ba5c4579
+size 1064

scores.json

@@ -0,0 +1 @@
+{"MRR": 0.2528349710865516, "R@5": 0.341842397336293, "R@10": 0.41509433962264153}

scores_data_cp_model_decorte.json

@@ -0,0 +1 @@
+{"MRR": 0.7816463522291275, "R@5": 0.8750261295428077, "R@10": 0.9099725266521337}

scores_data_free_model_decorte.json

@@ -0,0 +1 @@
+{"MRR": 0.7378132220027048, "R@5": 0.8122721490348084, "R@10": 0.8437422626721423}

scores_neural.json

@@ -0,0 +1 @@
+{"MRR": 0.24532786772257045, "R@5": 0.34476769431176724, "R@10": 0.41554494138080766}

scores_neural_rank_fusion.json

@@ -0,0 +1 @@
+{"MRR": 0.26586553241642275, "R@5": 0.3864524533217542, "R@10": 0.45288753799392095}

scores_neural_reranked30.json

@@ -0,0 +1 @@
+{"MRR": 0.19385869960671726, "R@5": 0.29396439426834564, "R@10": 0.39339991315675205}

scores_neural_skill_based.json

@@ -0,0 +1 @@
+{"MRR": 0.2725025462881446, "R@5": 0.3708206686930091, "R@10": 0.44203213200173685}

scores_rank_fusion.json

@@ -0,0 +1 @@
+{"MRR": 0.26293707481093864, "R@5": 0.3738601823708207, "R@10": 0.45115067303517153}

scores_reranked30.json

@@ -0,0 +1 @@
+{"MRR": 0.18424115910162434, "R@5": 0.2839774207555363, "R@10": 0.3821102909248806}

scores_skill_based.json

@@ -0,0 +1 @@
+{"MRR": 0.27219213765082034, "R@5": 0.3590968302214503, "R@10": 0.43595310464611375}

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 384,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "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 +1,72 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 384,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b92979f5d3b38eae52c57de30066b321039f8da2ef421751651d3d6f07c7e984
+size 5432

vector_transform_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc0fb14c3753637133ba10a31bc2f2cf15decdf4cc5ae8b0e10fd6b7435beb32
+size 3153352