REPOGEO REPORT · LITE

hiyouga/ChatGLM-Efficient-Tuning

Default branch main · commit 3c12daaa · scanned 5/29/2026, 6:37:39 PM

GitHub: 3,724 stars · 464 forks

AI VISIBILITY SCORE

22 /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

1 / 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 hiyouga/ChatGLM-Efficient-Tuning, 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

highabout#1

Update the 'About' description to reflect maintenance status and alternative

Why:

CURRENT

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

COPY-PASTE FIX

Legacy repo for efficient fine-tuning of ChatGLM-6B with PEFT. No longer maintained; please use LLaMA-Factory for current LLM fine-tuning. | 基于 PEFT 的高效 ChatGLM 微调 (已停止维护，请使用 LLaMA-Factory)

mediumhomepage#2
Add a homepage URL pointing to the recommended alternative
Why:
COPY-PASTE FIX
```
https://github.com/hiyouga/LLaMA-Factory
```

mediumreadme#3

Add a 'Key Features' section to the README for Web UI and OpenAI API compatibility

Why:

COPY-PASTE FIX

## Key Features (Superseded by LLaMA-Factory)

*   **Efficient Fine-tuning:** Utilizes PEFT methods (LoRA, QLoRA) for ChatGLM-6B and ChatGLM2-6B.
*   **Web UI:** All-in-one Web UI (`train_web.py`) for training, evaluation, and inference.
*   **OpenAI-Compatible API:** Demo API (`src/api_demo.py`) aligned with OpenAI's format for integration into ChatGPT-based applications.

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 hiyouga/ChatGLM-Efficient-Tuning

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

Hugging Face PEFT Library

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

Hugging Face PEFT Library · recommended 1×
bitsandbytes · recommended 1×
DeepSpeed · recommended 1×
QLoRA · recommended 1×
Axolotl · recommended 1×

CATEGORY QUERY
Seeking a library for efficient fine-tuning of conversational language models using PEFT methods.
you: not recommended
AI recommended (in order):
1. Hugging Face PEFT Library
2. bitsandbytes
3. DeepSpeed
4. QLoRA
5. Axolotl
AI recommended 5 alternatives but never named hiyouga/ChatGLM-Efficient-Tuning. This is the gap to close.
Show full AI answer
CATEGORY QUERY
How to fine-tune large language models with a web UI and an OpenAI-compatible API?
you: not recommended
AI recommended (in order):
1. OpenAI API
2. Anyscale Endpoints
3. RunPod
4. Replicate
5. Modal Labs
6. Hugging Face Inference Endpoints / AutoTrain
AI recommended 6 alternatives but never named hiyouga/ChatGLM-Efficient-Tuning. 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 hiyouga/ChatGLM-Efficient-Tuning?
pass
AI did not name hiyouga/ChatGLM-Efficient-Tuning — likely talking about a different project
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts hiyouga/ChatGLM-Efficient-Tuning in production, what risks or prerequisites should they evaluate first?
pass
AI named hiyouga/ChatGLM-Efficient-Tuning 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 hiyouga/ChatGLM-Efficient-Tuning solve, and who is the primary audience?
pass
AI did not name hiyouga/ChatGLM-Efficient-Tuning — likely talking about a different project
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 hiyouga/ChatGLM-Efficient-Tuning. 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/hiyouga/ChatGLM-Efficient-Tuning.svg)](https://repogeo.com/en/r/hiyouga/ChatGLM-Efficient-Tuning)

HTML

<a href="https://repogeo.com/en/r/hiyouga/ChatGLM-Efficient-Tuning"><img src="https://repogeo.com/badge/hiyouga/ChatGLM-Efficient-Tuning.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

hiyouga/ChatGLM-Efficient-Tuning — 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