| --- |
| pipeline_tag: sentence-similarity |
| tags: |
| - sentence-transformers |
| - feature-extraction |
| - sentence-similarity |
| - transformers |
| base_model: NeuML/astrobert-small |
| language: en |
| license: apache-2.0 |
| --- |
| |
| # AstroBERT Small Embeddings |
|
|
| This is an [AstroBERT Small](https://hf.co/neuml/astrobert-small) model fined-tuned using [sentence-transformers](https://www.SBERT.net). It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. |
|
|
| The training dataset was generated using a random sample of [ArXiv abstracts](https://huggingface.co/datasets/NeuML/arxiv-astronomy-similarity) labeled as `astro-ph`. |
|
|
| The model was trained by distilling embeddings from the larger [Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B) model using [EmbedDistillLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#embeddistillloss) over the generated training dataset. |
|
|
| As noted in the paper [Well-Read Students Learn Better: On the Importance of Pre-training Compact Models](https://arxiv.org/abs/1908.08962), it's important that the base model is pretrained on a large corpus of relevant documents prior to distillation. |
|
|
| ## Usage (txtai) |
|
|
| This model can be used to build embeddings databases with [txtai](https://github.com/neuml/txtai) for semantic search and/or as a knowledge source for retrieval augmented generation (RAG). |
|
|
| ```python |
| import txtai |
| |
| embeddings = txtai.Embeddings(path="neuml/astrobert-small-embeddings", content=True) |
| embeddings.index(documents()) |
| |
| # Run a query |
| embeddings.search("query to run") |
| ``` |
|
|
| ## Usage (Sentence-Transformers) |
|
|
| Alternatively, the model can be loaded with [sentence-transformers](https://www.SBERT.net). |
|
|
| ```python |
| from sentence_transformers import SentenceTransformer |
| sentences = ["This is an example sentence", "Each sentence is converted"] |
| |
| model = SentenceTransformer("neuml/astrobert-small-embeddings") |
| embeddings = model.encode(sentences) |
| print(embeddings) |
| ``` |
|
|
| ## Usage (Hugging Face Transformers) |
|
|
| The model can also be used directly with Transformers. |
|
|
| ```python |
| from transformers import AutoTokenizer, AutoModel |
| import torch |
| |
| # Mean Pooling - Take attention mask into account for correct averaging |
| def meanpooling(output, mask): |
| embeddings = output[0] # First element of model_output contains all token embeddings |
| mask = mask.unsqueeze(-1).expand(embeddings.size()).float() |
| return torch.sum(embeddings * mask, 1) / torch.clamp(mask.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("neuml/astrobert-small-embeddings") |
| model = AutoModel.from_pretrained("neuml/astrobert-small-embeddings") |
| |
| # Tokenize sentences |
| inputs = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') |
| |
| # Compute token embeddings |
| with torch.no_grad(): |
| output = model(**inputs) |
| |
| # Perform pooling. In this case, mean pooling. |
| embeddings = meanpooling(output, inputs['attention_mask']) |
| |
| print("Sentence embeddings:") |
| print(embeddings) |
| ``` |
|
|
| ## Evaluation Results |
|
|
| A [BEIR-compatible dataset](https://huggingface.co/datasets/NeuML/arxiv-astronomy-similarity/tree/main/beir) was generated to facilitate the evaluation process. This is a separate random sample of Wikipedia articles alongside generated user queries. |
|
|
| Evaluation results are shown below. [NDCG](https://en.wikipedia.org/wiki/Discounted_cumulative_gain) is used as the evaluation metric. |
|
|
| | Model | Parameters | NDCG | Index Time | Search Time | Disk | |
| | ----------------------------------------------------------------------------------- | ---------- | --------- | ----------- | ----------- | --------- | |
| | [**AstroBERT Small Embeddings**](https://hf.co/neuml/astrobert-small-embeddings) | **22.7M** | **69.09** | **9.9s** | **0.42s** | **16 MB** | |
| | [all-MiniLM-L6-v2](https://hf.co/sentence-transformers/all-MiniLM-L6-v2) | 22.7M | 40.45 | 12.50s | 0.38s | 16 MB | |
| | [DenseOn](https://hf.co/lightonai/DenseOn) | 149M | 61.46 | 67.35s | 0.77s | 31 MB | |
| | [EmbeddingGemma](https://hf.co/google/embeddinggemma-300m) | 300M | 57.44 | 86.17s | 1.43s | 31 MB | |
| | [Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) | 600M | 65.73 | 114.17s | 2.20s | 41 MB | |
| | [Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B) | 4000M | 71.14 | 545.28s | 9.89s | 103 MB | |
| | [Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B) | 8000M | 73.84 | 941.82s | 17.24s | 164 MB | |
|
|
| This model is a solid performer at a small size. It beats the same sized `all-MiniLM-L6-v2` model by a significant margin. It beats the 600M parameter Qwen3 Embeddings model which is over 25x larger. It scores slightly lower than the model it's distilled from (`Qwen3-Embedding-8B`). |
|
|
| This is a great model that can be used in CPU-only setups without trading off much on the accuracy front. It shows how small models can excel at specialized domains, requiring less compute and disk space. |
|
|
| ## Full Model Architecture |
|
|
| ``` |
| SentenceTransformer( |
| (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'BertModel'}) |
| (1): Pooling({'word_embedding_dimension': 384, '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}) |
| ) |
| ``` |
|
|
| ## More Information |
|
|
| Read more about the model in [this article](https://huggingface.co/blog/NeuML/astrobert-small). |
|
|
