Upload 14 files

.ipynb_checkpoints/mteb_eval-checkpoint.py

@@ -0,0 +1,71 @@
+import mteb
+from mteb.encoder_interface import PromptType
+from sentence_transformers import SentenceTransformer, models
+import numpy as np
+import torch
+import os
+import math
+
+model_save_path = "./" #REPLACE WITH YOUR PATH
+
+# Reload the prepared SentenceTransformer model
+model = SentenceTransformer(model_save_path)
+
+# -------- Step 3: Define Custom Model Interface for MTEB --------
+class CustomModel:
+    def __init__(self, model):
+        self.model = model
+
+    def encode(
+        self, 
+        sentences, 
+        task_name: str, 
+        prompt_type = None, 
+        max_batch_size: int = 32,  # Set default max batch size
+        **kwargs
+    ) -> np.ndarray:
+        """
+        Encodes the given sentences using the model with a maximum batch size.
+
+        Args:
+            sentences (List[str]): The sentences to encode.
+            task_name (str): The name of the task.
+            prompt_type (Optional[PromptType]): The prompt type to use.
+            max_batch_size (int): The maximum number of sentences to process in a single batch.
+            **kwargs: Additional arguments to pass to the encoder.
+
+        Returns:
+            np.ndarray: Encoded sentences as a numpy array.
+        """
+
+        sentences = [str(sentence) for sentence in sentences]
+        total_sentences = len(sentences)
+        num_batches = math.ceil(total_sentences / max_batch_size)
+        embeddings_list = []
+
+        for batch_idx in range(num_batches):
+            start_idx = batch_idx * max_batch_size
+            end_idx = min(start_idx + max_batch_size, total_sentences)
+            batch_sentences = sentences[start_idx:end_idx]
+            batch_embeddings = self.model.encode(batch_sentences, convert_to_tensor=True)
+
+            if not isinstance(batch_embeddings, torch.Tensor):
+                batch_embeddings = torch.tensor(batch_embeddings)
+
+            embeddings_list.append(batch_embeddings.cpu().numpy())
+
+        return np.vstack(embeddings_list)
+
+
+
+# Wrap the SentenceTransformer model in the CustomModel class
+custom_model = CustomModel(model)
+
+# Select the MTEB tasks to evaluate
+tasks = mteb.get_benchmark("MTEB(eng, classic)") 
+
+# Initialize the evaluation framework
+evaluation = mteb.MTEB(tasks=tasks)
+
+# Run evaluation and save results
+results = evaluation.run(custom_model, output_folder="results/model_results")

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "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

@@ -1,3 +1,141 @@
----
-license: apache-2.0
----
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+base_model: distilbert/distilbert-base-uncased
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on distilbert/distilbert-base-uncased
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) <!-- at revision 12040accade4e8a0f71eabdb258fecc2e7e948be -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### 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': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.3.1
+- Transformers: 4.48.0.dev0
+- PyTorch: 2.1.0a0+32f93b1
+- Accelerate: 1.2.0
+- Datasets: 2.21.0
+- Tokenizers: 0.21.0
+
+## Citation
+
+### BibTeX
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "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": "4.48.0.dev0",
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.48.0.dev0",
+    "pytorch": "2.1.0a0+32f93b1"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abaa3ca6ba670db88b0d70cf33d5545e3b45f7cb03d620accf05c7bc8974ea51
+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"
+  }
+]

mteb_eval.py

@@ -0,0 +1,71 @@
+import mteb
+from mteb.encoder_interface import PromptType
+from sentence_transformers import SentenceTransformer, models
+import numpy as np
+import torch
+import os
+import math
+
+model_save_path = "./" #REPLACE WITH YOUR PATH
+
+# Reload the prepared SentenceTransformer model
+model = SentenceTransformer(model_save_path)
+
+# -------- Step 3: Define Custom Model Interface for MTEB --------
+class CustomModel:
+    def __init__(self, model):
+        self.model = model
+
+    def encode(
+        self, 
+        sentences, 
+        task_name: str, 
+        prompt_type = None, 
+        max_batch_size: int = 32,  # Set default max batch size
+        **kwargs
+    ) -> np.ndarray:
+        """
+        Encodes the given sentences using the model with a maximum batch size.
+
+        Args:
+            sentences (List[str]): The sentences to encode.
+            task_name (str): The name of the task.
+            prompt_type (Optional[PromptType]): The prompt type to use.
+            max_batch_size (int): The maximum number of sentences to process in a single batch.
+            **kwargs: Additional arguments to pass to the encoder.
+
+        Returns:
+            np.ndarray: Encoded sentences as a numpy array.
+        """
+
+        sentences = [str(sentence) for sentence in sentences]
+        total_sentences = len(sentences)
+        num_batches = math.ceil(total_sentences / max_batch_size)
+        embeddings_list = []
+
+        for batch_idx in range(num_batches):
+            start_idx = batch_idx * max_batch_size
+            end_idx = min(start_idx + max_batch_size, total_sentences)
+            batch_sentences = sentences[start_idx:end_idx]
+            batch_embeddings = self.model.encode(batch_sentences, convert_to_tensor=True)
+
+            if not isinstance(batch_embeddings, torch.Tensor):
+                batch_embeddings = torch.tensor(batch_embeddings)
+
+            embeddings_list.append(batch_embeddings.cpu().numpy())
+
+        return np.vstack(embeddings_list)
+
+
+
+# Wrap the SentenceTransformer model in the CustomModel class
+custom_model = CustomModel(model)
+
+# Select the MTEB tasks to evaluate
+tasks = mteb.get_benchmark("MTEB(eng, classic)") 
+
+# Initialize the evaluation framework
+evaluation = mteb.MTEB(tasks=tasks)
+
+# Run evaluation and save results
+results = evaluation.run(custom_model, output_folder="results/model_results")

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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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]"
+}