This SLM does narrow tasks related to AI research papers! Should be run using the neural-txt harness: https://github.com/avbiswas/neural-txt

Part of the Neural Breakdown youtube course.

Install

# Base (no inference backend)
pip install neural-txt

# With HuggingFace backend (torch)
pip install neural-txt[hf]

# With MLX backend (Apple Silicon)
pip install neural-txt[mlx]

Quick start

from neuraltxt import NeuralTxt

model = NeuralTxt(backend="mlx")  # or backend="hf"

passage = """
Transformers have revolutionized NLP by introducing the self-attention
mechanism. Unlike RNNs, transformers process all tokens in parallel,
leading to significant training speedups.
"""

# Extract key points
bullets = model.extract_bullets(passage)

# Generate question-answer pairs
pairs = model.generate_qa_pairs(passage)

# Extract knowledge graph triplets
triplets = model.extract_triplets(passage)

JSON mode

Every method supports json=True for guaranteed structured output via outlines:

# Returns a BulletsOutput pydantic model
bullets = model.extract_bullets(passage, json=True)
print(bullets.bullets)  # list[str]

# Returns a QAPairsOutput pydantic model
qa = model.generate_qa_pairs(passage, json=True)
for pair in qa.pairs:
    print(pair.question, pair.answer)

# Returns a TripletsOutput pydantic model
triplets = model.extract_triplets(passage, json=True)
for t in triplets.triplets:
    print(t.subject, t.relation, t.object)

API

Benchmarks

On research paper QA and retrieval tasks, this model handsomely beats other edge LMs.

How these models are made

All this is part of this YouTube course by Neural Breakdown:

• Course Video 1 (CPT): https://youtu.be/B8Ur62D3J3U
• Course Video 2 (SFT): https://youtu.be/gvZIUEL6Ruc
• Course Video 3 (DPO): https://youtu.be/qQwg2nFtZ1Y