REPOGEO REPORT · LITE

IST-DASLab/sparsegpt

Default branch master · commit 147d2159 · scanned 6/10/2026, 12:43:35 PM

GitHub: 884 stars · 123 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE

53 /100

Needs work

Category recall

1 / 2

Avg rank #6.0 when recommended

Rule findings

1 pass · 1 warn · 0 fail

Objective metadata checks

AI knows your name

3 / 3

Direct prompts that named your repo

HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface IST-DASLab/sparsegpt, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION

hightopics#1

Add relevant topics to the repository

Why:

CURRENT

(none)

COPY-PASTE FIX

llm-pruning, model-compression, large-language-models, one-shot-pruning, sparse-models, deep-learning, pytorch, transformers, nlp

highreadme#2

Reposition the README's opening statement to highlight deployment benefits

Why:

CURRENT

This repository contains code to reproduce the key results of the paper SparseGPT: Massive Language Models Can be Accurately Pruned in One-shot.

COPY-PASTE FIX

SparseGPT offers a cutting-edge, one-shot method for accurately pruning massive language models, significantly reducing their size and computational cost for efficient deployment. This repository provides the code to reproduce the key results of our ICML 2023 paper.

mediumreadme#3

Add a 'Why SparseGPT?' section to highlight its core differentiator

Why:

COPY-PASTE FIX

## Why SparseGPT?
SparseGPT stands out with its **one-shot, post-training pruning** method for large language models. Unlike iterative or retraining-heavy approaches, it accurately compresses models by solving a local quadratic problem layer-wise, minimizing activation reconstruction error on a small calibration dataset. This makes it uniquely efficient for achieving high sparsity and accuracy in models like OPT and BLOOM.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall

1 / 2

50% of queries surface IST-DASLab/sparsegpt

Avg rank

#6.0

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

TensorFlow Model Optimization Toolkit

Recommended in 2 of 2 queries

COMPETITOR LEADERBOARD

TensorFlow Model Optimization Toolkit · recommended 2×
bitsandbytes · recommended 1×
ONNX Runtime · recommended 1×
NVIDIA TensorRT · recommended 1×
Hugging Face Transformers · recommended 1×

CATEGORY QUERY
How to efficiently reduce the size of large language models for deployment?
you: not recommended
AI recommended (in order):
1. bitsandbytes
2. ONNX Runtime
3. NVIDIA TensorRT
4. Hugging Face Transformers
5. PaddlePaddle PaddleSlim
6. PyTorch Pruning
7. TensorFlow Model Optimization Toolkit
8. TinyLlama
9. MobileBERT
10. DistilBERT
11. TransformerXL
12. ALBERT
13. Longformer
14. BigBird
AI recommended 14 alternatives but never named IST-DASLab/sparsegpt. This is the gap to close.
Show full AI answer
CATEGORY QUERY
What are effective methods for one-shot pruning of transformer-based language models?
you: #6
AI recommended (in order):
1. Hugging Face Optimum
2. PyTorch Pruning Utilities
3. TensorFlow Model Optimization Toolkit
4. DeepSpeed
5. PyTorch-Pruning
6. SparseGPT ← you
Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

Metadata completeness
warn
Suggestion:
README presence
pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

Compared to common alternatives in this category, what is the core differentiator of IST-DASLab/sparsegpt?
pass
AI named IST-DASLab/sparsegpt explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts IST-DASLab/sparsegpt in production, what risks or prerequisites should they evaluate first?
pass
AI named IST-DASLab/sparsegpt explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
In one sentence, what problem does the repo IST-DASLab/sparsegpt solve, and who is the primary audience?
pass
AI named IST-DASLab/sparsegpt explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of IST-DASLab/sparsegpt. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/IST-DASLab/sparsegpt.svg)](https://repogeo.com/en/r/IST-DASLab/sparsegpt)

HTML

<a href="https://repogeo.com/en/r/IST-DASLab/sparsegpt"><img src="https://repogeo.com/badge/IST-DASLab/sparsegpt.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

IST-DASLab/sparsegpt — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

Deep reports10 / month
Brand-free category queries5 vs 2 in Lite
Prioritized action items8 vs 3 in Lite