Nasa Smd Ibm Distil V0.1

🚀 Model Card for INDUS - Small (nasa - smd - ibm - distil - v0.1)

INDUS - Small (nasa - smd - ibm - distil - v0.1) is a distilled version of the RoBERTa - based, Encoder - only transformer model INDUS (nasa - impact/nasa - smd - ibm - v0.1). It is domain - adapted for NASA Science Mission Directorate (SMD) applications. The model is fine - tuned on scientific journals and articles relevant to NASA SMD, aiming to enhance natural language technologies such as information retrieval and intelligent search.

We trained the smaller model, INDUS_SMALL, with 38M parameters through knowledge distillation techniques using INDUS as the teacher. INDUS_SMALL follows a 4 - layer architecture recommended by the Neural Architecture Search engine (Trivedi et al., 2023), which offers an optimal trade - off between performance and latency. We adopted the distillation objective proposed in MiniLMv2 (Wang et al., 2021) to transfer fine - grained self - attention relations, which is considered the current state - of - the - art (Udagawa et al., 2023). Using this objective, we trained the model for 500K steps with an effective batch size of 480 on 30 V100 GPUs.

📚 Documentation

✨ Features

• Model Adaptation: Domain - adapted for NASA SMD applications, enhancing its performance in relevant scientific fields.
• Knowledge Distillation: Trained using knowledge distillation techniques to reduce the number of parameters while maintaining performance.
• Optimal Architecture: Follows a 4 - layer architecture recommended by the Neural Architecture Search engine for a good balance between performance and latency.

🔧 Technical Details

• Base Model: INDUS
• Tokenizer: Custom
• Original version Parameters: 125M
• Pretraining Strategy: Masked Language Modeling (MLM)
• Distilled Version Parameters: 38 Million Parameters

📦 Training Data

• Wikipedia English (Feb 1, 2020)
• AGU Publications
• AMS Publications
• Scientific papers from Astrophysics Data Systems (ADS)
• PubMed abstracts
• PubMedCentral (PMC) (commercial license subset)


📋 Training Procedure

• Framework: fairseq 0.12.1 with PyTorch 1.9.1
• transformers Version: 4.2.0
• Strategy: Masked Language Modeling (MLM)

📊 Evaluation

BLURB benchmark

 (Standard deviation across 10 random seeds in parenthesis. Macro avg. reported across datasets and micro avg. computed by averaging scores on each task then averaging across task averages.)

Climate Change NER, and NASA - QA benchmark

 (Climate Change NER and NASA - QA benchmark results. Standard Deviation over multiple runs given in parantheses)

Please refer to the following dataset cards for further benchmarks and evaluation:

• NASA - IR Benchmark - https://huggingface.co/datasets/nasa - impact/nasa - smd - IR - benchmark
• NASA - QA Benchmark - https://huggingface.co/datasets/nasa - impact/nasa - smd - qa - benchmark
• Climate Change NER Benchmark - https://huggingface.co/datasets/ibm/Climate - Change - NER

💻 Uses

• Named Entity Recognition (NER)
• Information Retrieval
• Sentence Transformers
• Extractive QA

For NASA SMD related, scientific usecases.

📄 License

This model is released under the Apache - 2.0 license.

📝 Note

This Model is released in support of the training and evaluation of the encoder language model ["Indus"](https://huggingface.co/nasa - impact/nasa - smd - ibm - v0.1).

Accompanying paper can be found here: https://arxiv.org/abs/2405.10725

📚 Citation

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

@misc {nasa - impact_2023,
	author       = {Masayasu Maraoka and Bishwaranjan Bhattacharjee and Muthukumaran Ramasubramanian and Ikhsa Gurung and Rahul Ramachandran and Manil Maskey and Kaylin Bugbee and Rong Zhang and Yousef El Kurdi and Bharath Dandala and Mike Little and Elizabeth Fancher and Lauren Sanders and Sylvain Costes and Sergi Blanco - Cuaresma and Kelly Lockhart and Thomas Allen and Felix Grazes and Megan Ansdell and Alberto Accomazzi and Sanaz Vahidinia and Ryan McGranaghan and Armin Mehrabian and Tsendgar Lee},
	title        = { nasa - smd - ibm - v0.1 (Revision f01d42f) },
	year         = 2023,
	url          = { https://huggingface.co/nasa - impact/nasa - smd - ibm - v0.1 },
	doi          = { 10.57967/hf/1429 },
	publisher    = { Hugging Face }
}

👥 Attribution

• IBM Research: Masayasu Muraoka, Bishwaranjan Bhattacharjee, Rong Zhang, Yousef El Kurdi, Bharath Dandala
• 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 Encoder - only 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.