RRepoGEO

REPOGEO REPORT · LITE

LianjiaTech/BELLE

Default branch main · commit 645084d3 · scanned 6/28/2026, 11:26:52 AM

GitHub: 8,271 stars · 761 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
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 LianjiaTech/BELLE, 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 more specific topics for Chinese LLM, ASR, and multimodal capabilities

    Why:

    CURRENT
    bloom, chinese-nlp, gpt-evaluation, gpt-q, instruct-finetune, instruct-gpt, instruction-set, llama, lora, open-models
    COPY-PASTE FIX
    bloom, chinese-nlp, gpt-evaluation, gpt-q, instruct-finetune, instruct-gpt, instruction-set, llama, lora, open-models, chinese-llm, large-language-model, speech-recognition, asr, multimodal-llm, instruction-tuning
  • mediumhomepage#2
    Add a homepage URL to the repository settings

    Why:

    COPY-PASTE FIX
    https://huggingface.co/BelleGroup
  • lowreadme#3
    Briefly mention ASR and multimodal capabilities in the README's opening

    Why:

    CURRENT
    本项目的目标是促进中文对话大模型开源社区的发展，愿景是成为能够帮到每一个人的LLM Engine。相比如何做好大语言模型的预训练，BELLE更关注如何在开源预训练大语言模型的基础上，帮助每一个人都能够得到一个属于自己的、效果尽可能好的具有指令表现能力的语言模型，降低大语言模型、特别是中文大语言模型的研究和应用门槛。为此，BELLE项目会持续开放指令训练数据、相关模型、训练代码、应用场景等，也会持续评估不同训练数据、训练算法等对模型表现的影响。BELLE针对中文做了优化，模型调优仅使用由ChatGPT生产的数据（不包含任何其他数据）。
    COPY-PASTE FIX
    本项目的目标是促进中文对话大模型开源社区的发展，愿景是成为能够帮到每一个人的LLM Engine。BELLE致力于在开源预训练大语言模型的基础上，帮助每一个人都能够得到一个属于自己的、效果尽可能好的具有指令表现能力的语言模型，降低大语言模型、特别是中文大语言模型的研究和应用门槛。为此，BELLE项目会持续开放指令训练数据、相关模型、训练代码、应用场景等，也会持续评估不同训练数据、训练算法等对模型表现的影响。BELLE针对中文做了优化，模型调优仅使用由ChatGPT生产的数据（不包含任何其他数据），并持续扩展到语音识别（ASR）和多模态大语言模型领域。

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 LianjiaTech/BELLE
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Baichuan 2
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Baichuan 2 · recommended 1×
  2. Qwen · recommended 1×
  3. ChatGLM3 · recommended 1×
  4. InternLM2 · recommended 1×
  5. Yi · recommended 1×
  • CATEGORY QUERY
    Looking for an open-source large language model engine optimized for Chinese instruction tuning.
    you: not recommended
    AI recommended (in order):
    1. Baichuan 2
    2. Qwen
    3. ChatGLM3
    4. InternLM2
    5. Yi

    AI recommended 5 alternatives but never named LianjiaTech/BELLE. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    How can I build a custom instruction-following Chinese language model with open-source tools?
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers
    2. Hugging Face Datasets
    3. PyTorch
    4. TensorFlow
    5. LoRA (Low-Rank Adaptation)
    6. QLoRA
    7. peft
    8. DeepSpeed
    9. FSDP (Fully Sharded Data Parallel)
    10. WandB (Weights & Biases)
    11. MLflow
    12. FastChat
    13. vLLM
    14. Label Studio
    15. Doccano

    AI recommended 15 alternatives but never named LianjiaTech/BELLE. 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 LianjiaTech/BELLE?
    pass
    AI named LianjiaTech/BELLE explicitly

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

  • If a team adopts LianjiaTech/BELLE in production, what risks or prerequisites should they evaluate first?
    pass
    AI named LianjiaTech/BELLE 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 LianjiaTech/BELLE solve, and who is the primary audience?
    pass
    AI named LianjiaTech/BELLE 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 LianjiaTech/BELLE. 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/LianjiaTech/BELLE.svg)](https://repogeo.com/en/r/LianjiaTech/BELLE)
HTML
<a href="https://repogeo.com/en/r/LianjiaTech/BELLE"><img src="https://repogeo.com/badge/LianjiaTech/BELLE.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

LianjiaTech/BELLE — 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