Upload folder using huggingface_hub

README.md

@@ -1,84 +1,101 @@
 ---
+base_model:
+- minishlab/potion-base-8M
+language:
+- en
 library_name: model2vec
 license: mit
-model_name: tmpqsu1ee6a
+model_name: tmppmj8rbw3
 tags:
 - embeddings
 - static-embeddings
-datasets:
-- HuggingFaceFW/fineweb-edu-llama3-annotations
-language:
-- en
-base_model:
-- minishlab/potion-base-8M
+- sentence-transformers
 ---
 
-# potion-8m-edu-classifier Model Card
+# tmppmj8rbw3 Model Card
 
-This [Model2Vec](https://github.com/MinishLab/model2vec) model is a fine-tuned version of [potion-base-8m](https://huggingface.co/minishlab/potion-base-8M).
-It was trained to predict educational content, analogous to how the [fineweb-edu-classifier](https://huggingface.co/HuggingFaceFW/fineweb-edu-classifier) was used to filter educational content.
+This [Model2Vec](https://github.com/MinishLab/model2vec) model is a distilled version of the ['minishlab/potion-base-8M'](https://huggingface.co/['minishlab/potion-base-8M']) Sentence Transformer. It uses static embeddings, allowing text embeddings to be computed orders of magnitude faster on both GPU and CPU. It is designed for applications where computational resources are limited or where real-time performance is critical. Model2Vec models are the smallest, fastest, and most performant static embedders available. The distilled models are up to 50 times smaller and 500 times faster than traditional Sentence Transformers.
 
-It achieves the following performance on the evaluation split:
 
+## Installation
+
+Install model2vec using pip:
 ```
-              precision    recall  f1-score   support
-
-           0       0.70      0.42      0.52      5694
-           1       0.75      0.86      0.80     26512
-           2       0.55      0.51      0.53     10322
-           3       0.54      0.45      0.49      3407
-           4       0.59      0.30      0.40       807
-           5       0.00      0.00      0.00         1
-
-    accuracy                           0.69     46743
-   macro avg       0.52      0.42      0.46     46743
-weighted avg       0.68      0.69      0.68     46743
+pip install model2vec
 ```
 
-When thresholded to a binary classifier, it achieves a macro-averaged F1-score of `0.79`. The original classifier achieves `0.81` on the same dataset, but this classifier is orders of magnitude faster on CPU.
+## Usage
 
-```
-              precision    recall  f1-score   support
+### Using Model2Vec
 
-     not edu       0.96      0.98      0.97     42528
-         edu       0.70      0.54      0.61      4215
+The [Model2Vec library](https://github.com/MinishLab/model2vec) is the fastest and most lightweight way to run Model2Vec models.
 
-    accuracy                           0.94     46743
-   macro avg       0.83      0.76      0.79     46743
-weighted avg       0.93      0.94      0.93     46743
-```
+Load this model using the `from_pretrained` method:
+```python
+from model2vec import StaticModel
 
-## Installation
+# Load a pretrained Model2Vec model
+model = StaticModel.from_pretrained("tmppmj8rbw3")
 
-Install model2vec with the inference extra using pip:
+# Compute text embeddings
+embeddings = model.encode(["Example sentence"])
 ```
-pip install model2vec[inference]
+
+### Using Sentence Transformers
+
+You can also use the [Sentence Transformers library](https://github.com/UKPLab/sentence-transformers) to load and use the model:
+
+```python
+from sentence_transformers import SentenceTransformer
+
+# Load a pretrained Sentence Transformer model
+model = SentenceTransformer("tmppmj8rbw3")
+
+# Compute text embeddings
+embeddings = model.encode(["Example sentence"])
 ```
 
-## Usage
-Load this model using the `from_pretrained` method:
+### Distilling a Model2Vec model
+
+You can distill a Model2Vec model from a Sentence Transformer model using the `distill` method. First, install the `distill` extra with `pip install model2vec[distill]`. Then, run the following code:
+
 ```python
-from model2vec.inference import StaticModelPipeline
+from model2vec.distill import distill
 
-# Load a pretrained Model2Vec model
-model = StaticModelPipeline.from_pretrained("minishlab/potion-8m-edu-classifier")
+# Distill a Sentence Transformer model, in this case the BAAI/bge-base-en-v1.5 model
+m2v_model = distill(model_name="BAAI/bge-base-en-v1.5", pca_dims=256)
 
-# Predict labels
-label = model.predict(["Example sentence"])
+# Save the model
+m2v_model.save_pretrained("m2v_model")
 ```
 
+## How it works
+
+Model2vec creates a small, fast, and powerful model that outperforms other static embedding models by a large margin on all tasks we could find, while being much faster to create than traditional static embedding models such as GloVe. Best of all, you don't need any data to distill a model using Model2Vec.
+
+It works by passing a vocabulary through a sentence transformer model, then reducing the dimensionality of the resulting embeddings using PCA, and finally weighting the embeddings using [SIF weighting](https://openreview.net/pdf?id=SyK00v5xx). During inference, we simply take the mean of all token embeddings occurring in a sentence.
+
+## Additional Resources
+
+- [Model2Vec Repo](https://github.com/MinishLab/model2vec)
+- [Model2Vec Base Models](https://huggingface.co/collections/minishlab/model2vec-base-models-66fd9dd9b7c3b3c0f25ca90e)
+- [Model2Vec Results](https://github.com/MinishLab/model2vec/tree/main/results)
+- [Model2Vec Tutorials](https://github.com/MinishLab/model2vec/tree/main/tutorials)
+- [Website](https://minishlab.github.io/)
+
+
 ## Library Authors
 
-Model2Vec was developed by [Minish](https://github.com/MinishLab).
+Model2Vec was developed by the [Minish Lab](https://github.com/MinishLab) team consisting of [Stephan Tulkens](https://github.com/stephantul) and [Thomas van Dongen](https://github.com/Pringled).
 
 ## Citation
 
 Please cite the [Model2Vec repository](https://github.com/MinishLab/model2vec) if you use this model in your work.
 ```
-@software{minishlab2024model2vec,
-  authors = {Stephan Tulkens, Thomas van Dongen},
-  title = {Model2Vec: Turn any Sentence Transformer into a Small Fast Model},
+@article{minishlab2024model2vec,
+  author = {Tulkens, Stephan and {van Dongen}, Thomas},
+  title = {Model2Vec: Fast State-of-the-Art Static Embeddings},
   year = {2024},
-  url = {https://github.com/MinishLab/model2vec},
+  url = {https://github.com/MinishLab/model2vec}
 }
 ```

config.json

@@ -1 +1,3 @@
-{"normalize": true}
+{
+    "normalize": true
+}

modules.json

@@ -0,0 +1,14 @@
+[
+    {
+        "idx": 0,
+        "name": "0",
+        "path": ".",
+        "type": "sentence_transformers.models.StaticEmbedding"
+    },
+    {
+        "idx": 1,
+        "name": "1",
+        "path": "1_Normalize",
+        "type": "sentence_transformers.models.Normalize"
+    }
+]

pipeline.skops

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9adbbe7b32b5370c5f017d5e40fb43ae0c0fdb6b0ca818c33b64bbbc43194e45
-size 3820674
+oid sha256:b927aac5eeba88323d576d0f108e1cef48bd7641f2cad10fffb216acaa552f72
+size 3842044