mpnet-base-nli-matryoshka

mpnet-base-nli-matryoshka/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

mpnet-base-nli-matryoshka/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
+}

mpnet-base-nli-matryoshka/README.md

@@ -0,0 +1,132 @@
+---
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+
+---
+
+# tomaarsen/mpnet-base-nli-matryoshka
+
+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.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317233cc92fd6fee317e030/5O_UxEzuU_RHkOIAZyV_K.png)
+
+<!--- 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('tomaarsen/mpnet-base-nli-matryoshka')
+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('tomaarsen/mpnet-base-nli-matryoshka')
+model = AutoModel.from_pretrained('tomaarsen/mpnet-base-nli-matryoshka')
+
+# 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=tomaarsen/mpnet-base-nli-matryoshka)
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 8807 with parameters:
+```
+{'batch_size': 64}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MatryoshkaLoss.MatryoshkaLoss` with parameters:
+  ```
+  {'loss': 'MultipleNegativesRankingLoss', 'matryoshka_dims': [768, 512, 256, 128, 64], 'matryoshka_weights': [1, 1, 1, 1, 1]}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 1,
+    "evaluation_steps": 880,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 881,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: MPNetModel 
+  (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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

mpnet-base-nli-matryoshka/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "tomaarsen/mpnet-base-nli-matryoshka",
+  "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": "4.48.3",
+  "vocab_size": 30527
+}

mpnet-base-nli-matryoshka/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.2.0.dev0",
+    "transformers": "4.48.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

mpnet-base-nli-matryoshka/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228fb7ea27e469d85fad12e8e8fdaaf7a015985fb3429316cbbf8d9d24980007
+size 437967672

mpnet-base-nli-matryoshka/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"
+  }
+]

mpnet-base-nli-matryoshka/onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b49fade0836ccee996d5d6d852b3dad2fa109c4f5acf6e0bd23c8942cfd04962
+size 435826548

mpnet-base-nli-matryoshka/onnx/model_O1.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d9af3ce50837e4c95e28d5776447aa8395bc786aa0dfbe78da0f98892e7ebb
+size 435730180

mpnet-base-nli-matryoshka/onnx/model_O2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a6f298911b538040b5e33069aa0b962bad1d68847256ed487abb0e9b1d99a9
+size 435666661

mpnet-base-nli-matryoshka/onnx/model_O3.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa144a73c5f88793a2be46ba5f8bc70113b0f8a45ffe4ca3ed09d3b7faf8b89b
+size 435666516

mpnet-base-nli-matryoshka/onnx/model_O4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3c2f730057d66bfe0e28bcb2fbbc058bee750210dd14df2e0ce36acd7c85af
+size 217894954

mpnet-base-nli-matryoshka/onnx/model_qint8_avx512.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386a28ff93e7654261f6a2d0447b1dea85d7ed9fbf045455eb93299574bf0c3c
+size 110124379

mpnet-base-nli-matryoshka/onnx/model_quint8_avx2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b3d1856e42acb3858abc015dfd8117b176a9eec1daaca7767401176e6d93c3
+size 110124376

mpnet-base-nli-matryoshka/openvino/openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21f300d61dd5bd201ff72137ed98eb076505ccf5aa0f5c13072069ff4b48b74a
+size 435583684

mpnet-base-nli-matryoshka/sentence_bert_config.json

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

mpnet-base-nli-matryoshka/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/tomaarsen/mpnet-base-nli-matryoshka

mpnet-base-nli-matryoshka/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
+  }
+}

mpnet-base-nli-matryoshka/tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 384,
+  "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]"
+}

mpnet-base-nli-matryoshka/training_nli_matryoshka.py

@@ -0,0 +1,106 @@
+# Matryoshka test
+from collections import defaultdict
+from typing import Dict
+import datasets
+from datasets import Dataset
+from sentence_transformers import (
+    SentenceTransformer,
+    SentenceTransformerTrainer,
+    losses,
+    evaluation,
+    TrainingArguments
+)
+from sentence_transformers.models import Transformer, Pooling
+
+def to_triplets(dataset):
+    premises = defaultdict(dict)
+    for sample in dataset:
+        premises[sample["premise"]][sample["label"]] = sample["hypothesis"]
+    queries = []
+    positives = []
+    negatives = []
+    for premise, sentences in premises.items():
+        if 0 in sentences and 2 in sentences:
+            queries.append(premise)
+            positives.append(sentences[0]) # <- entailment
+            negatives.append(sentences[2]) # <- contradiction
+    return Dataset.from_dict({
+        "anchor": queries,
+        "positive": positives,
+        "negative": negatives,
+    })
+
+snli_ds = datasets.load_dataset("snli")
+snli_ds = datasets.DatasetDict({
+    "train": to_triplets(snli_ds["train"]),
+    "validation": to_triplets(snli_ds["validation"]),
+    "test": to_triplets(snli_ds["test"]),
+})
+multi_nli_ds = datasets.load_dataset("multi_nli")
+multi_nli_ds = datasets.DatasetDict({
+    "train": to_triplets(multi_nli_ds["train"]),
+    "validation_matched": to_triplets(multi_nli_ds["validation_matched"]),
+})
+
+all_nli_ds = datasets.DatasetDict({
+    "train": datasets.concatenate_datasets([snli_ds["train"], multi_nli_ds["train"]]),
+    "validation": datasets.concatenate_datasets([snli_ds["validation"], multi_nli_ds["validation_matched"]]),
+    "test": snli_ds["test"]
+})
+
+stsb_dev = datasets.load_dataset("mteb/stsbenchmark-sts", split="validation")
+stsb_test = datasets.load_dataset("mteb/stsbenchmark-sts", split="test")
+
+training_args = TrainingArguments(
+    output_dir="checkpoints",
+    num_train_epochs=1,
+    seed=42,
+    per_device_train_batch_size=64,
+    per_device_eval_batch_size=64,
+    learning_rate=2e-5,
+    warmup_ratio=0.1,
+    bf16=True,
+    logging_steps=10,
+    evaluation_strategy="steps",
+    eval_steps=300,
+    save_steps=1000,
+    save_total_limit=2,
+    metric_for_best_model="spearman_cosine",
+    greater_is_better=True,
+)
+
+transformer = Transformer("microsoft/mpnet-base", max_seq_length=384)
+pooling = Pooling(transformer.get_word_embedding_dimension(), pooling_mode="mean")
+model = SentenceTransformer(modules=[transformer, pooling])
+
+tokenizer = model.tokenizer
+loss = losses.MultipleNegativesRankingLoss(model)
+loss = losses.MatryoshkaLoss(model, loss, [768, 512, 256, 128, 64])
+
+dev_evaluator = evaluation.EmbeddingSimilarityEvaluator(
+    stsb_dev["sentence1"],
+    stsb_dev["sentence2"],
+    [score / 5 for score in stsb_dev["score"]],
+    main_similarity=evaluation.SimilarityFunction.COSINE,
+    name="sts-dev",
+)
+
+trainer = SentenceTransformerTrainer(
+    model=model,
+    evaluator=dev_evaluator,
+    args=training_args,
+    train_dataset=all_nli_ds["train"],
+    # eval_dataset=all_nli_ds["validation"],
+    loss=loss,
+)
+trainer.train()
+
+test_evaluator = evaluation.EmbeddingSimilarityEvaluator(
+    stsb_test["sentence1"],
+    stsb_test["sentence2"],
+    [score / 5 for score in stsb_test["score"]],
+    main_similarity=evaluation.SimilarityFunction.COSINE,
+    name="sts-test",
+)
+results = test_evaluator(model)
+print(results)