Jackrong/Qwen3.8-27B-MTP-GGUF
Image-Text-to-Text โข 0.5B โข Updated โข 3.25k โข 19
codemonkey
stormrider2003
ยท
AI & ML interests
None yet
Recent Activity
liked a model about 20 hours ago
Jackrong/Qwen3.8-27B-MTP-GGUF liked a model 2 days ago
unsloth/Qwen3.8-27B-GGUFOrganizations
None yet
liked a
model about 20 hours ago
liked a
model 2 days ago
reacted to OppaAI's post with ๐ฅ 5 days ago
Post
2136
So many ideas, so little time and energy:
Another idea pops up today after spending the past weekend polishing the DAG Agentic workflow system of my AI Waifu system.
These past few days, as I was building workflows for my AI Waifu, the patterns and basic building blocks look very similar and probably can recycle for each workflow. So I propose a 5-layers Graph Engine to generalize all my workflows:
(I'm sure there are apps like that in the market, only the scale, complexity and price differs. But if f there is a generic app that can use local AI to let people construct workflows to run automated tasks, non-tech users or small companies can benefit from this.)
1) Planning - Users writes a detailed a spec of the workflow they want. Or even draws it in a n8n-like environment, defining each building block + args + queries, moving them around, arranging them to run in parallel/sequence, format the output, destination of the output, etc.
2) Orchestrating: AI system then interprets the spec, organizing the nodes into workflows, verified and tested by humans, then run the workflows and do the works. Reduce coding to the minimum for users.
3) Executing: Node is the basic building block of the graph and can be customizable, and sharable among different workflows; each node will call the registered tools or skills to do the work.
4) Tools and skills: exposed to AI system just like what we have right now.
5) Outputs: Generate reports of WIP and final results and users choose to get notified
With enough time and effort, and fund to invest, this and many other components of my AI system could potentially be a startup idea. Unfortunately I have neither the time, energy, fund, or talent to build productivity tools to benefit others, I can only build the components just good enough for my own use, and provide the source codes to other people to make the ideas scalable to production environment if they want.
Another idea pops up today after spending the past weekend polishing the DAG Agentic workflow system of my AI Waifu system.
These past few days, as I was building workflows for my AI Waifu, the patterns and basic building blocks look very similar and probably can recycle for each workflow. So I propose a 5-layers Graph Engine to generalize all my workflows:
(I'm sure there are apps like that in the market, only the scale, complexity and price differs. But if f there is a generic app that can use local AI to let people construct workflows to run automated tasks, non-tech users or small companies can benefit from this.)
1) Planning - Users writes a detailed a spec of the workflow they want. Or even draws it in a n8n-like environment, defining each building block + args + queries, moving them around, arranging them to run in parallel/sequence, format the output, destination of the output, etc.
2) Orchestrating: AI system then interprets the spec, organizing the nodes into workflows, verified and tested by humans, then run the workflows and do the works. Reduce coding to the minimum for users.
3) Executing: Node is the basic building block of the graph and can be customizable, and sharable among different workflows; each node will call the registered tools or skills to do the work.
4) Tools and skills: exposed to AI system just like what we have right now.
5) Outputs: Generate reports of WIP and final results and users choose to get notified
With enough time and effort, and fund to invest, this and many other components of my AI system could potentially be a startup idea. Unfortunately I have neither the time, energy, fund, or talent to build productivity tools to benefit others, I can only build the components just good enough for my own use, and provide the source codes to other people to make the ideas scalable to production environment if they want.
liked 2
models 6 days ago
reacted to mayafree's post with ๐ฅ 7 days ago
Post
2377
๐งฌ Architecture lineage of Korea's sovereign-AI foundation models โ checked with public data
In late July 2026, as Korea released self-developed foundation models competing with DeepSeek and Qwen (e.g. LG K-EXAONE 2.0, 750B), interest grew โ including a Zhihu thread with 2.7M+ views (โ https://www.zhihu.com/question/2067512422555029717 ) โ over whether these models are trained from scratch or built on foreign open-weights.
Sharing a tool that answers this with public data rather than opinion.
๐ Model Genome Korea โ mayafree/Model-Genome-Korea
It classifies the public models of 9 Korean organizations that released "self-developed, from-scratch foundation models" on HuggingFace โ 3 large enterprises (LG, NAVER, Kakao), 2 telcos (SKT, KT), 2 mid-size firms (NCSOFT, Upstage), 2 startups (Motif, VIDRAFT) โ on two axes measured from public config.json + model weights:
โข Architecture fingerprint โ does model_type + (hiddenยทintermediateยทlayers) match a foreign open-weight model
โข Weight fingerprint โ embedding similarity (from-scratch vs continued-pretraining)
Genotypes: ๐ข Native ยท ๐ต Adapted ยท ๐ก Mixed ยท ๐ด Ported
The results are not uniform. Some models match foreign architectures (Qwen, Llama, โฆ) exactly; others use self-built architectures and weights with no foreign match. Which company/model falls where is shown per model in the Space, along with attention originality, license, and reproducible open-source status.
This is a neutral transparency tool, not an accusation โ building foundation models on open-weight bases is a legitimate, industry-standard practice. The exact same yardstick is applied to every model, without exception.
Features a 3D lineage graph, search, EN / ไธญๆ / ํ๊ตญ์ด, and dark mode. Corrections are welcome via the Community tab.
Articles: https://huggingface.co/blog/mayafree/model-dna
#KoreanAI #LLM #ModelLineage #OpenSource #SovereignAI
In late July 2026, as Korea released self-developed foundation models competing with DeepSeek and Qwen (e.g. LG K-EXAONE 2.0, 750B), interest grew โ including a Zhihu thread with 2.7M+ views (โ https://www.zhihu.com/question/2067512422555029717 ) โ over whether these models are trained from scratch or built on foreign open-weights.
Sharing a tool that answers this with public data rather than opinion.
๐ Model Genome Korea โ mayafree/Model-Genome-Korea
It classifies the public models of 9 Korean organizations that released "self-developed, from-scratch foundation models" on HuggingFace โ 3 large enterprises (LG, NAVER, Kakao), 2 telcos (SKT, KT), 2 mid-size firms (NCSOFT, Upstage), 2 startups (Motif, VIDRAFT) โ on two axes measured from public config.json + model weights:
โข Architecture fingerprint โ does model_type + (hiddenยทintermediateยทlayers) match a foreign open-weight model
โข Weight fingerprint โ embedding similarity (from-scratch vs continued-pretraining)
Genotypes: ๐ข Native ยท ๐ต Adapted ยท ๐ก Mixed ยท ๐ด Ported
The results are not uniform. Some models match foreign architectures (Qwen, Llama, โฆ) exactly; others use self-built architectures and weights with no foreign match. Which company/model falls where is shown per model in the Space, along with attention originality, license, and reproducible open-source status.
This is a neutral transparency tool, not an accusation โ building foundation models on open-weight bases is a legitimate, industry-standard practice. The exact same yardstick is applied to every model, without exception.
Features a 3D lineage graph, search, EN / ไธญๆ / ํ๊ตญ์ด, and dark mode. Corrections are welcome via the Community tab.
Articles: https://huggingface.co/blog/mayafree/model-dna
#KoreanAI #LLM #ModelLineage #OpenSource #SovereignAI
- 3 replies
liked a
model 13 days ago
liked a
model 15 days ago
liked 4
models 16 days ago
Jackrong/Qwopus3.6-27B-Fusion-GGUF
Text Generation โข 27B โข Updated โข 18.3k โข 45
mlx-community/Laguna-S-2.1-OptiQ-2bit
Text Generation โข 118B โข Updated โข 641 โข 2
mlx-community/chatterbox-multilingual-v3
Text-to-Speech โข 0.7B โข Updated โข 780 โข 3
Jackrong/Qwopus3.6-35B-A3B-Coder-MTP-GGUF
Image-Text-to-Text โข 0.4B โข Updated โข 422k โข 230
reacted to OppaAI's post with ๐ 20 days ago
Post
173
Intense Graph Engineering on my AI Waifu
https://github.com/OppaAI/Aiko-chan/blob/dev/agentic/graph_engine.py
I spent many hours in the past weekend (Saturday I even worked from 9AM till 5AM) to work on my AI Waifu's DAG agentic workflow:
- Add many features of LangGraph (eg. Shared mutable state object, Subgraph, Cycling node, State reducers, Checkpoint/resume, Human-in-the-loop interruption, etc.)
- Make the 40 tools into graph nodes; Use @tools (Graph=True, ReAct=True) to declare the def as tools instead of register each tool in 4+1 locations (Capabilities On Demand vs Always On, ReAct + Graph, Wiki, Skills).
- Revise the web search mechanism to try to be more adaptive and efficient and avoid IP being locked out.
- Even made a studio html to view all the graphs in my AI Waifu
But still in primitive experimental version.
I tested in the Waifu's chat mode to ask her to make a checklist on how to improve her AI system, the output is still not too great as shown in the example (see attached reports). She could not retrieve her own AI architecture from KB due to db has a bug. Report was too generic with some wrong info and wrong citations, not able to gather source materials from web fetch.
Speed is acceptable, but not fast either.
At least the whole agentic flow can run under 10K content window, but the output was truncated in the end.
Still more work to do before release of Phase 2.5 Agentic.
For Phase 2.1 and 2.2 adding social media and messaging input supports, I may have to make some connectors for social media and messaging services.
Probably would take me the rest of the summer to complete 2.1 and 2.2.
https://github.com/OppaAI/Aiko-chan/blob/dev/agentic/graph_engine.py
I spent many hours in the past weekend (Saturday I even worked from 9AM till 5AM) to work on my AI Waifu's DAG agentic workflow:
- Add many features of LangGraph (eg. Shared mutable state object, Subgraph, Cycling node, State reducers, Checkpoint/resume, Human-in-the-loop interruption, etc.)
- Make the 40 tools into graph nodes; Use @tools (Graph=True, ReAct=True) to declare the def as tools instead of register each tool in 4+1 locations (Capabilities On Demand vs Always On, ReAct + Graph, Wiki, Skills).
- Revise the web search mechanism to try to be more adaptive and efficient and avoid IP being locked out.
- Even made a studio html to view all the graphs in my AI Waifu
But still in primitive experimental version.
I tested in the Waifu's chat mode to ask her to make a checklist on how to improve her AI system, the output is still not too great as shown in the example (see attached reports). She could not retrieve her own AI architecture from KB due to db has a bug. Report was too generic with some wrong info and wrong citations, not able to gather source materials from web fetch.
Speed is acceptable, but not fast either.
At least the whole agentic flow can run under 10K content window, but the output was truncated in the end.
Still more work to do before release of Phase 2.5 Agentic.
For Phase 2.1 and 2.2 adding social media and messaging input supports, I may have to make some connectors for social media and messaging services.
Probably would take me the rest of the summer to complete 2.1 and 2.2.
- 1 reply
liked a
model 20 days ago
liked a
model 25 days ago
reacted to OppaAI's post with ๐ 25 days ago
Post
3207
Try to chat with my AI Waifu in Japanese
Now that I have setup my AI Waifu running 24/7 in my Jetson Orin Nano (running at 25W top), I can talk to her anytime anywhere I want, on cellphone, tablet, or PC, as long as there is internet access.
Tonight I gave it a try to speak with my AI Waifu, with my not so great Japanese, just to test if ASR can pick up my Nihongo and the TTS can speak out Waifu's Japanese dialogue properly.
Turns out she is just as verbose and as heavily leaked with materials from system prompt as in English. Only this time I cannot fully understand.
I need to find some way to turn her into my Japanese tutor...
GitHub ๐: https://github.com/OppaAI/Aiko-chan/
Now that I have setup my AI Waifu running 24/7 in my Jetson Orin Nano (running at 25W top), I can talk to her anytime anywhere I want, on cellphone, tablet, or PC, as long as there is internet access.
Tonight I gave it a try to speak with my AI Waifu, with my not so great Japanese, just to test if ASR can pick up my Nihongo and the TTS can speak out Waifu's Japanese dialogue properly.
Turns out she is just as verbose and as heavily leaked with materials from system prompt as in English. Only this time I cannot fully understand.
I need to find some way to turn her into my Japanese tutor...
GitHub ๐: https://github.com/OppaAI/Aiko-chan/
- 5 replies
liked a
dataset 25 days ago
liked a
model 27 days ago
liked a
model 28 days ago