Nasa Smd Ibm St V2

🚀 Indus-Retriever Model Card

Indus-Retriever (nasa-smd-ibm-st-v2) is a Bi-encoder sentence transformer model fine-tuned from the nasa-smd-ibm-v0.1 encoder model. It's an updated version of nasa-smd-ibm-st with better performance. Trained with 271 million examples and a domain-specific dataset of 2.6 million examples from documents curated by NASA Science Mission Directorate (SMD), this model aims to enhance natural language technologies such as information retrieval and intelligent search for SMD NLP applications.

You can also use the distilled version of the model here: Distilled Model

🚀 Quick Start

from sentence_transformers import SentenceTransformer, Util

model = SentenceTransformer("nasa-impact/nasa-smd-ibm-st-v2")

input_queries = [
'query: how much protein should a female eat', 'query: summit define']
input_passages = [
"As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments."]
query_embeddings = model.encode(input_queries)
passage_embeddings = model.encode(input_passages)
print(util.cos_sim(query_embeddings, passage_embeddings))

✨ Features

• Enhanced Performance: An updated version of nasa-smd-ibm-st with better performance.
• Domain-Specific Training: Trained with a domain-specific dataset from NASA SMD documents.
• Multiple Use Cases: Suitable for information retrieval and sentence similarity search in NASA SMD related scientific usecases.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

from sentence_transformers import SentenceTransformer, Util

model = SentenceTransformer("nasa-impact/nasa-smd-ibm-st-v2")

input_queries = [
'query: how much protein should a female eat', 'query: summit define']
input_passages = [
"As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments."]
query_embeddings = model.encode(input_queries)
passage_embeddings = model.encode(input_passages)
print(util.cos_sim(query_embeddings, passage_embeddings))

📚 Documentation

Model Details

Training Data

Figure: Open dataset sources for sentence transformers (269M in total)

Additionally, 2.6M abstract + title pairs collected from NASA SMD documents.

Training Procedure

Evaluation

The following models are evaluated:

1. All-MiniLM-l6-v2 [sentence-transformers/all-MiniLM-L6-v2]
2. BGE-base [BAAI/bge-base-en-v1.5]
3. RoBERTa-base [roberta-base]
4. nasa-smd-ibm-rtvr_v0.1 [nasa-impact/nasa-smd-ibm-st]

Figure: BEIR and NASA-IR Evaluation Metrics

🔧 Technical Details

The model is fine-tuned from the nasa-smd-ibm-v0.1 encoder model. It uses sentence pairs and a relevance score for training. The model encodes the two sentence pairs independently and calculates the cosine similarity, which is then optimized using the relevance score.

📄 License

This project is licensed under the Apache-2.0 license.

Citation

If you find this work useful, please cite using the following bibtex citation:

@misc {nasa-impact_2024,
	author       = { {NASA-IMPACT} },
	title        = { nasa-smd-ibm-st-v2 (Revision d249d84) },
	year         = 2024,
	url          = { https://huggingface.co/nasa-impact/nasa-smd-ibm-st-v2 },
	doi          = { 10.57967/hf/1800 },
	publisher    = { Hugging Face }
}

Attribution

• IBM Research: Aashka Trivedi, Masayasu Muraoka, Bishwaranjan Bhattacharjee
• NASA SMD: Muthukumaran Ramasubramanian, Iksha Gurung, Rahul Ramachandran, Manil Maskey, Kaylin Bugbee, Mike Little, Elizabeth Fancher, Lauren Sanders, Sylvain Costes, Sergi Blanco-Cuaresma, Kelly Lockhart, Thomas Allen, Felix Grazes, Megan Ansdell, Alberto Accomazzi, Sanaz Vahidinia, Ryan McGranaghan, Armin Mehrabian, Tsendgar Lee

Disclaimer

This sentence-transformer model is currently in an experimental phase. We are working to improve the model's capabilities and performance, and as we progress, we invite the community to engage with this model, provide feedback, and contribute to its evolution.