RRepoGEO

REPOGEO REPORT · LITE

autoliuweijie/FastBERT

Default branch master · commit 859632f6 · scanned 5/30/2026, 2:52:58 AM

GitHub: 608 stars · 90 forks

AI VISIBILITY SCORE
35 /100
Critical
Category recall
0 / 2
Not recommended in any query
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 autoliuweijie/FastBERT, 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
  • highlicense#1
    Add a LICENSE file to the repository

    Why:

    COPY-PASTE FIX
    Create a LICENSE file in the repository root with the appropriate license text (e.g., MIT, Apache-2.0, or the license under which the original paper was published).
  • highreadme#2
    Reposition the README's opening statement to highlight the problem and solution

    Why:

    CURRENT
    # FastBERT

Source code for "FastBERT: a Self-distilling BERT with Adaptive Inference Time".
    COPY-PASTE FIX
    # FastBERT

Accelerate BERT inference with FastBERT, a self-distilling model that uses adaptive computation to achieve significant speedups without substantial accuracy loss. This repository provides the official implementation for "FastBERT: a Self-distilling BERT with Adaptive Inference Time" (ACL2020).
  • mediumtopics#3
    Expand repository topics to include key technical terms

    Why:

    CURRENT
    acl2020, bert, fastbert
    COPY-PASTE FIX
    acl2020, bert, fastbert, adaptive-inference, early-exit, model-compression, nlp-acceleration, inference-optimization, knowledge-distillation

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
0 / 2
0% of queries surface autoliuweijie/FastBERT
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
microsoft/onnxruntime
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. microsoft/onnxruntime · recommended 2×
  2. huggingface/transformers · recommended 2×
  3. openvinotoolkit/openvino · recommended 2×
  4. NVIDIA TensorRT · recommended 1×
  5. TimDettmers/bitsandbytes · recommended 1×
  • CATEGORY QUERY
    How to improve inference speed for large language models without significant accuracy loss?
    you: not recommended
    AI recommended (in order):
    1. NVIDIA TensorRT
    2. bitsandbytes (TimDettmers/bitsandbytes)
    3. ONNX Runtime (microsoft/onnxruntime)
    4. Hugging Face Transformers (huggingface/transformers)
    5. OpenVINO Toolkit (openvinotoolkit/openvino)
    6. Google's Medusa
    7. DeepSpeed-MII (microsoft/DeepSpeed-MII)
    8. FlashAttention (Dao-AILab/flash-attention)
    9. xFormers (facebookresearch/xformers)
    10. vLLM (vllm-project/vllm)
    11. PyTorch 2.0 (pytorch/pytorch)

    AI recommended 11 alternatives but never named autoliuweijie/FastBERT. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a method for adaptive inference to accelerate pre-trained language model predictions.
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers (huggingface/transformers)
    2. Optimum (huggingface/optimum)
    3. ONNX Runtime (microsoft/onnxruntime)
    4. OpenVINO Toolkit (openvinotoolkit/openvino)
    5. TensorRT (NVIDIA/TensorRT)
    6. DeepSpeed (microsoft/DeepSpeed)
    7. TVM (apache/tvm)

    AI recommended 7 alternatives but never named autoliuweijie/FastBERT. This is the gap to close.

    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 autoliuweijie/FastBERT?
    pass
    AI named autoliuweijie/FastBERT explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts autoliuweijie/FastBERT in production, what risks or prerequisites should they evaluate first?
    pass
    AI named autoliuweijie/FastBERT 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 autoliuweijie/FastBERT solve, and who is the primary audience?
    pass
    AI named autoliuweijie/FastBERT 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 autoliuweijie/FastBERT. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/autoliuweijie/FastBERT.svg)](https://repogeo.com/en/r/autoliuweijie/FastBERT)
HTML
<a href="https://repogeo.com/en/r/autoliuweijie/FastBERT"><img src="https://repogeo.com/badge/autoliuweijie/FastBERT.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

autoliuweijie/FastBERT — 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