v1

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "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
+}

README.md

@@ -1,3 +1,129 @@
----
-license: apache-2.0
----
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
+model = AutoModel.from_pretrained('{MODEL_NAME}')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 30 with parameters:
+```
+{'batch_size': 10, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 20,
+    "evaluation_steps": -1,
+    "evaluator": "src.data.IrEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 6e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 0,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel 
+  (1): Pooling({'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})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "/home/sbhargav/.cache/torch/sentence_transformers/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.40.2",
+    "pytorch": "2.3.0+cu121"
+  }
+}

eval/Information-Retrieval_evaluation_dev2_results.csv

@@ -0,0 +1,21 @@
+epoch,steps,cos_sim-Accuracy@1000,cos_sim-Precision@1000,cos_sim-Recall@1000,cos_sim-MRR@1000,cos_sim-NDCG@10,cos_sim-NDCG@1000,cos_sim-MAP@1000,dot_score-Accuracy@1000,dot_score-Precision@1000,dot_score-Recall@1000,dot_score-MRR@1000,dot_score-NDCG@10,dot_score-NDCG@1000,dot_score-MAP@1000
+0,-1,1.0,0.0010000000000000002,1.0,0.21478264165219874,0.2654187903251689,0.3647205719047765,0.21478264165219874,1.0,0.0010000000000000002,1.0,0.1765448955743,0.22276776356656483,0.3253456249149124,0.17654489557430006
+1,-1,1.0,0.0010000000000000002,1.0,0.23031055133959144,0.2746423606300469,0.37352192135174483,0.23031055133959144,1.0,0.0010000000000000002,1.0,0.16116246733664852,0.19528828917405788,0.31252840054752035,0.16116246733664857
+2,-1,1.0,0.0010000000000000002,1.0,0.2383370163671117,0.2883509512375327,0.3826862609192197,0.23833701636711163,1.0,0.0010000000000000002,1.0,0.19819666867135277,0.2507022672025061,0.3467474561398994,0.19819666867135283
+3,-1,1.0,0.0010000000000000002,1.0,0.24637383756632006,0.28992012211590235,0.3865205215227734,0.24637383756631992,1.0,0.0010000000000000002,1.0,0.19783645621287102,0.23811451109512793,0.3452348739484996,0.19783645621287113
+4,-1,1.0,0.0010000000000000002,1.0,0.2557476734165179,0.2966803482091579,0.3957932200186219,0.25574767341651766,1.0,0.0010000000000000002,1.0,0.20823103354324754,0.24815140813977554,0.35469422697570885,0.20823103354324757
+5,-1,1.0,0.0010000000000000002,1.0,0.25756658380784053,0.2989068305046046,0.39380323104667836,0.25756658380784025,1.0,0.0010000000000000002,1.0,0.20437947243168494,0.2525261553225652,0.3496621197214021,0.2043794724316849
+6,-1,1.0,0.0010000000000000002,1.0,0.23669045791896753,0.2804258456624145,0.38035758053755186,0.23669045791896745,1.0,0.0010000000000000002,1.0,0.20975338393256387,0.26075703370118947,0.35551409625305647,0.20975338393256387
+7,-1,1.0,0.0010000000000000002,1.0,0.2737882744689679,0.31171596459545403,0.4102114051123706,0.2737882744689678,1.0,0.0010000000000000002,1.0,0.24438387394513172,0.27600432363260474,0.38510689522452357,0.24438387394513172
+8,-1,1.0,0.0010000000000000002,1.0,0.26494423733598255,0.30832544722327154,0.40202668605917824,0.2649442373359824,1.0,0.0010000000000000002,1.0,0.21722168085477975,0.25874603116307354,0.36265460604362987,0.2172216808547797
+9,-1,1.0,0.0010000000000000002,1.0,0.26094359915856363,0.3044546975127253,0.39899784302507024,0.2609435991585635,1.0,0.0010000000000000002,1.0,0.22261176656523182,0.2683569519897886,0.3669187287387258,0.2226117665652317
+10,-1,1.0,0.0010000000000000002,1.0,0.269390808631807,0.3152140275643737,0.4062630677045657,0.2693908086318068,1.0,0.0010000000000000002,1.0,0.23118253247694098,0.2755125138473274,0.37430345302078566,0.2311825324769409
+11,-1,1.0,0.0010000000000000002,1.0,0.2730847159534095,0.32024940855765205,0.4104054486890142,0.27308471595340944,1.0,0.0010000000000000002,1.0,0.2269044694743224,0.27821982154420577,0.3721995471484176,0.2269044694743225
+12,-1,1.0,0.0010000000000000002,1.0,0.279196089268259,0.32485476763603627,0.41379654167771546,0.2791960892682589,1.0,0.0010000000000000002,1.0,0.2231122958332923,0.27899167086501536,0.368056164661416,0.22311229583329237
+13,-1,1.0,0.0010000000000000002,1.0,0.2753154284869351,0.3201150230583376,0.4109468195346987,0.27531542848693497,1.0,0.0010000000000000002,1.0,0.23153649693602252,0.28220717522626226,0.3750097567553414,0.23153649693602238
+14,-1,1.0,0.0010000000000000002,1.0,0.2784425030707504,0.32938109226349593,0.4140191568082857,0.27844250307075025,1.0,0.0010000000000000002,1.0,0.24016439644121898,0.289559450484183,0.3823046204628328,0.24016439644121892
+15,-1,1.0,0.0010000000000000002,1.0,0.2823079687517416,0.33051415699870157,0.4174743001837484,0.2823079687517415,1.0,0.0010000000000000002,1.0,0.23763818376383805,0.2863916567312545,0.38114435370445005,0.2376381837638379
+16,-1,1.0,0.0010000000000000002,1.0,0.26681816983793866,0.3209140189385327,0.40560284906173577,0.2668181698379386,1.0,0.0010000000000000002,1.0,0.2300070511833308,0.28030617760569226,0.3747302250744342,0.23000705118333079
+17,-1,1.0,0.0010000000000000002,1.0,0.27013705725012205,0.3218974688609506,0.4075391173401515,0.2701370572501219,1.0,0.0010000000000000002,1.0,0.22542751756062027,0.27506332707783193,0.37064872603511956,0.22542751756062018
+18,-1,1.0,0.0010000000000000002,1.0,0.26682658699873474,0.3195330568205544,0.40530654626640855,0.26682658699873457,1.0,0.0010000000000000002,1.0,0.22761415599019932,0.27876562150455425,0.3727079685310349,0.2276141559901992
+19,-1,1.0,0.0010000000000000002,1.0,0.26654827028275446,0.32117103467843794,0.4051199190694705,0.26654827028275424,1.0,0.0010000000000000002,1.0,0.23214366018228147,0.2821787226335282,0.37618398308539,0.23214366018228139

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c14049a0196ca0d2b392198462dbc9c34c1890af4bf4a9bf4ef8a4a08060771c
+size 265462608

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

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 +1,55 @@
+{
+  "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]"
+}