Astrosage 8B

🚀 AstroSage-Llama-3.1-8B

AstroSage-Llama-3.1-8B is a domain - specialized natural - language AI assistant designed for astronomy, astrophysics, and cosmology research. It's trained on a vast dataset, including astronomy - related arXiv papers from 2007 - 2024, millions of synthetic question - answer pairs, and other astronomical literature. This enables it to handle a wide range of questions proficiently, highlighting the potential of domain - specialized AI.

🚀 Quick Start

To use the AstroSage-Llama-3.1-8B model, you can follow the code example below:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
model = AutoModelForCausalLM.from_pretrained("AstroMLab/AstroSage-8b", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("AstroMLab/AstroSage-8b")

# Function to generate a response
def generate_response(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

    outputs = model.generate(
        **inputs,
        max_new_tokens=128,
        do_sample=True,
        pad_token_id=tokenizer.eos_token_id,
    )
    response = outputs[0][inputs['input_ids'].shape[-1]:]
    decoded = tokenizer.decode(response, skip_special_tokens=True)

    return decoded

# Example usage
prompt = """
You are an expert in general astrophysics. Your task is to answer the following question:
What are the main components of a galaxy?
"""
response = generate_response(prompt)
print(response)

✨ Features

• Domain - Specialized: Tailored for astronomy, astrophysics, and cosmology research.
• High Proficiency: Demonstrates excellent performance on a wide range of astronomical questions.
• Cost - Effective: ~1000x more cost - effective than proprietary models.

📦 Installation

The installation process is mainly about loading the model and tokenizer using the transformers library as shown in the quick - start code.

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("AstroMLab/AstroSage-8b", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("AstroMLab/AstroSage-8b")

prompt = "What is the Big Bang theory?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=128, do_sample=True, pad_token_id=tokenizer.eos_token_id)
response = outputs[0][inputs['input_ids'].shape[-1]:]
decoded = tokenizer.decode(response, skip_special_tokens=True)
print(decoded)

📚 Documentation

Model Details

Model Improvements and Performance

AstroSage-Llama-3.1-8B shows remarkable performance improvements:

The model demonstrates:

• Outperformance of all 8B parameter models
• Comparable performance to GPT-4o (80.4%)
• ~1000x more cost - effective than proprietary models
• 7 percentage - point improvement over base Llama - 3.1 - 8b model

Training Data

• Continued Pre - training:

  • ~250,000 arXiv preprints (2007 - 2024) from astro - ph and gr - qc
  • Astronomy - related Wikipedia articles
  • Selected astronomy textbooks
  • Total: 3.3 billion tokens, 19.9 GB plaintext

• Supervised Fine - tuning:

  • 8.8 million curated QA pairs
  • Filtered Infinity - Instruct - 7M dataset
  • Paper summaries and metadata
  • Total: 2.0 billion tokens, 9.8 GB plaintext

Intended Use

• Curiosity - driven question answering
• Brainstorming new ideas
• Astronomical research assistance
• Educational support in astronomy
• Literature review and summarization
• Scientific explanation of concepts

Limitations

• Training data cutoff: January 2024
• As with all LLMs, hallucinations are possible
• Limited by 8B parameter size for complex reasoning
• Paper metadata not perfectly memorized
• Performance primarily validated on multiple - choice questions
• Primarily trained for use in English

Technical Specifications

• Architecture: Based on Meta - Llama 3.1
• Training Infrastructure: ORNL OLCF Frontier
• Hosting: Hugging Face Hub (AstroMLab/AstroSage-8B)

Ethical Considerations

While this model is designed for scientific use:

• Should not be used as sole source for critical research decisions
• Output should be verified against primary sources
• May reflect biases present in astronomical literature

Citation and Contact

• Corresponding author: Tijmen de Haan (tijmen dot dehaan at gmail dot com)
• AstroMLab: astromachinelearninglab at gmail dot com
• Please cite the AstroMLab 3 paper when referencing this model:

@preprint{dehaan2024astromlab3,
      title={AstroMLab 3: Achieving GPT-4o Level Performance in Astronomy with a Specialized 8B-Parameter Large Language Model}, 
      author={Tijmen de Haan and Yuan-Sen Ting and Tirthankar Ghosal and Tuan Dung Nguyen and Alberto Accomazzi and Azton Wells and Nesar Ramachandra and Rui Pan and Zechang Sun},
      year={2024},
      eprint={2411.09012},
      archivePrefix={arXiv},
      primaryClass={astro-ph.IM},
      url={https://arxiv.org/abs/2411.09012}, 
}