← Back to Product Feed

GitHub Open Source jingyaogong/minimind-o

🎙️ 「大模型」从0训练0.1B能听能说能看的全模态Omni模型!A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!

1,210
Traction Score
140
Forks
May 1, 2026
Launch Date
View Origin Link

Product Positioning & Context

🎙️ 「大模型」从0训练0.1B能听能说能看的全模态Omni模型!A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!
artificial-intelligence chatgpt omni

Related Ecosystem & Alternatives

Discover adjacent products, open-source repositories, and developer tools sharing similar technical architecture.

Deep-Dive FAQs

What is jingyaogong/minimind-o?
jingyaogong/minimind-o is a digital product or tool described as: 🎙️ 「大模型」从0训练0.1B能听能说能看的全模态Omni模型!A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!
Where did jingyaogong/minimind-o originate?
Data for jingyaogong/minimind-o was aggregated directly from the GitHub Open Source community ecosystem, representing raw developer and early-adopter sentiment.
When was jingyaogong/minimind-o publicly launched?
The initial public indexing or launch date for jingyaogong/minimind-o within our tracked developer communities was recorded on May 1, 2026.
How popular is jingyaogong/minimind-o?
jingyaogong/minimind-o has achieved measurable traction, logging over 1,210 traction score and facilitating 140 recorded discussions or engagements.
Which technical categories define jingyaogong/minimind-o?
Based on metadata extraction, jingyaogong/minimind-o is categorized under topics such as: artificial-intelligence, chatgpt, omni.
Are there active development issues for jingyaogong/minimind-o?
Yes, we are currently tracking open architectural debates and bug reports for this project on GitHub. There are currently 3 active high-priority issues logged recently.
What are some commercial alternatives to jingyaogong/minimind-o?
Our semantic intelligence engine identifies potential commercial alternatives in the SaaS space, such as SocialKaptan, which offers overlapping value propositions.
How does the creator describe jingyaogong/minimind-o?
The original author or development team describes the product as follows: "🎙️ 「大模型」从0训练0.1B能听能说能看的全模态Omni模型!A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!"

Active Developer Issues (GitHub)

open Apple Silicon (MPS + MLX) 原生推理支持 — 提 PR 前征询意见
Logged: May 9, 2026
open Interested in supporting in SGlang omni
Logged: May 8, 2026
open Interest in adding MiniMind-O to vLLM-Omni?
Logged: May 6, 2026

Community Voice & Feedback

linyueqian • May 7, 2026
Thanks! I will open an issue and see if anyone in the community wants to support.
jingyaogong • May 7, 2026
Thank you for the invitation! vLLM-Omni is an amazing and great inference framework. In fact, a large portion of MiniMind-O's synthetic training data was sampled using vLLM-Omni driving Qwen-TTS!

You are more than welcome to adapt the code and merge it into vLLM-Omni. I’d be very happy to review the architecture part.
At the same time, I’ll also take some time to study the PR examples you mentioned (#2319, #2462, #3388) and try to submit a PR on my side for your review. We can move forward in parallel — you follow your own pace, and I’ll treat this as a learning opportunity. As for which PR gets merged or how to combine them, I’ll leave it entirely up to the vLLM-Omni team.

Finally, thank you for noticing MiniMind-O, a project that is just starting to sprout. Your support is what keeps me motivated. Thank you!

Discovery Source

GitHub Open Source GitHub Open Source

Aggregated via automated community intelligence tracking.

Tech Stack Dependencies

No direct open-source NPM package mentions detected in the product documentation.

Media Tractions & Mentions

No mainstream media stories specifically mentioning this product name have been intercepted yet.

Deep Research & Science

No direct peer-reviewed scientific literature matched with this product's architecture.