Taichu-AI/ZDTaichu5.0-9B
About the project
ZDTaichu5.0-9B is a multimodal foundation model built on Qwen3.5-9B and C-RADIOv4-H for image, video, spatial and embodied reasoning, and agentic tasks.
Useful for
- Run the model for OCR and chart/diagram understanding on images and documents
- Use it for spatial reasoning and planning in embodied AI and VLA tasks
- Apply it for multi-step tool use in agentic scenarios
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 0 stars so far today, about 54 expected by the end of the day. The usual pace is 0 per day, so that's 54× as much.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 15 days old and already has 879 stars.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 879
- Stars in a day
- 54
- Forks
- 191
- Issues and pull requests
- 4
- Watchers
- 143
- Language
- Python
- License
- Apache-2.0
- Created
- September 4, 2026
- Last push
- September 17, 2026
Star trust
Unusual star pattern. The magnitude is lowered, not zeroed:
- Stars arrived in one batch on a single day (718) and stopped right after: 70 over the next two days. Real interest usually fades gradually.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 19, 2026Top new repositories this month: #100
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/Taichu-AI/ZDTaichu5.0-9B)Similar projects
-
7.9
TheoLeeCJ/SemIf
An open reproduction of the Jev-style semantic decision interface: reads typed option probabilities directly from a 4B model's logits without generating text. Runs on a single RTX 3090.
-
6.6
TianyuCodings/NanoJev
A nano replica of Jev built on Qwen3-0.6B that outputs probability distributions over candidates in a single forward pass with no token decoding, plus a training pipeline and game demos (maze, Snake).
-
6.6
Continuum-AI-Corp/OrcaBonsai-27B-Uncensored
A tool for runtime refusal ablation in the compressed Ternary Bonsai 2 27B LLM: it projects the residual stream to remove the refusal direction without modifying or re-quantizing weights. Runs on Apple Silicon via MLX.
-
6.0
jaredpalmer/kev
kev is a LoRA adapter with a small readout head on top of Qwen2.5-0.5B that answers many typed questions about a document in a single forward pass, returning calibrated probabilities instead of text.
-
5.4
vinnylarouge/jevlike
A small trainable model that picks one option from a changing list of text options in a single forward pass, an open alternative to TypeSafe's Jev. Aimed at developers who need fast classification or menu selection…
-
5.3
zhengkid/Dream-RSI
Research project on recursive self-improvement: past discovery histories become a replay simulator used to evaluate and refine exploration policies. Code is still being prepared; paper and demo are available.