RRepoGEO

REPOGEO REPORT · LITE

salesforce/xgen

Default branch main · commit c2efe4af · scanned 6/6/2026, 12:42:05 PM

GitHub: 727 stars · 38 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 salesforce/xgen, 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
  • highreadme#1
    Reposition README H1 and opening paragraph to explicitly state XGen is an LLM for long sequence modeling

    Why:

    CURRENT
    # XGen

Official research release for the family of **XGen** models (`7B`) by Salesforce AI Research:
    COPY-PASTE FIX
    # XGen: Open-Source Large Language Models (LLMs) for Long Sequence Modeling

This is the official research release for the family of **XGen** models (`7B`) by Salesforce AI Research. XGen is a collection of open-source Large Language Models (LLMs) specifically designed for advanced long sequence modeling, supporting context windows up to 8K tokens.
  • highhomepage#2
    Add a homepage URL to the repository About section

    Why:

    COPY-PASTE FIX
    https://huggingface.co/Salesforce
  • mediumreadme#3
    Add a 'Key Capabilities' section to the README

    Why:

    CURRENT
    The README directly moves from the research paper title/authors to "Models".
    COPY-PASTE FIX
    ## Key Capabilities

*   **Long Sequence Modeling:** XGen models are specifically trained to handle extensive text inputs, supporting context windows up to 8K tokens.
*   **Efficient Processing:** Designed for efficient processing of long documents, making them suitable for tasks requiring deep contextual understanding.
*   **Open-Source Access:** Freely available for research and development, with models published on the HuggingFace Hub.

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 salesforce/xgen
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Gemma 7B Instruct
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Gemma 7B Instruct · recommended 2×
  2. Llama 2 70B-Chat · recommended 1×
  3. Mistral 7B Instruct v0.2 · recommended 1×
  4. Mixtral 8x7B Instruct v0.1 · recommended 1×
  5. CodeLlama - 70B Instruct · recommended 1×
  • CATEGORY QUERY
    What open-source large language models support 8k token context windows?
    you: not recommended
    AI recommended (in order):
    1. Llama 2 70B-Chat
    2. Mistral 7B Instruct v0.2
    3. Mixtral 8x7B Instruct v0.1
    4. CodeLlama - 70B Instruct
    5. Vicuna-33B v1.3
    6. Gemma 7B Instruct

    AI recommended 6 alternatives but never named salesforce/xgen. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking an efficient, open-source LLM for processing very long text documents.
    you: not recommended
    AI recommended (in order):
    1. Mistral 7B Instruct
    2. Mistral Large
    3. Llama 3 8B Instruct
    4. Llama 3 70B Instruct
    5. Qwen 1.5 7B Chat
    6. Qwen 1.5 72B Chat
    7. Yi-34B-200K
    8. Gemma 2B
    9. Gemma 7B Instruct
    10. Phi-3-mini-4k-instruct
    11. Phi-3-mini-128k-instruct

    AI recommended 11 alternatives but never named salesforce/xgen. 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 salesforce/xgen?
    pass
    AI named salesforce/xgen explicitly

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

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

Subscribe to Pro for deep diagnoses

salesforce/xgen — 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
salesforce/xgen — RepoGEO report