Downloads · 30 days
330
100% of all-time downloads
turnercore/needle-automaticity-v10
needle-automaticity-v10 is a text generation model from turnercore. Use it when you need the model to write or continue text. It is set up for needle-point. The card lists the license as apache-2.0.
Needle Automaticity V10 is a compact bounded tool-calling model for the Needle Point runtime. It is intended for fast sensing, finite one-off actions, and simple expression—not open-ended planning or unconstrained too…
Downloads · 30 days
330
100% of all-time downloads
All-time downloads
330
Public
Parameters
26.2M
105 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors105 MB · 100%
From the Hugging Face model README
Needle Automaticity V10 is a compact bounded tool-calling model for the Needle Point runtime. It is intended for fast sensing, finite one-off actions, and simple expression—not open-ended planning or unconstrained tool arguments.
The model uses 36 allowed capabilities with closed enum, const, boolean, and finite-array argument domains. Open-ended capabilities are excluded.
The checkpoint was trained with upstream JAX Needle pinned to commit
ffb1c5144c5a16cb8ec650dbc8a6f6fd3854f8f2 and converted for Needle Point.
Training used a 1,767-row JEV-assisted corpus. JEV was used to audit labels and
identify hard examples for additional exposure; teacher responses were not
copied into the training labels. All action disagreements were manually
reviewed and canonical gold labels were retained.
Acceptance was run through Needle Point strict constrained decoding on a family-isolated 360-case benchmark:
| Lane | Exact match |
|---|---|
| Action/tool call | 215/216 (99.5370%) |
| Hard no-tool boundary | 144/144 (100%) |
| Combined | 359/360 (99.7222%) |
All outputs parsed and validated, no boundary case overcalled, and no constraint fallback occurred.
A later 100-case fresh adversarial holdout produced 56% exact match: 53.33% on 60 action cases and 60% on 40 hard no-tool cases, with 98% valid outputs. This is the more conservative estimate of robustness to novel adversarial wording; the 99.72% result is specific to the curated V10 held-out distribution. The unassisted gold checkpoint scored 58% on the same fresh holdout (36.67% action, 90% no-tool), showing that assisted hard-example weighting traded higher action recall for substantially lower boundary precision.
model.safetensors:
7bf8417fb2dc6ff03f33549e959e6aa4dd06898ab4a3d7d160f63bee1e4693afconfig.json:
bb90a73f354403511e0c83df8a5962e04752be831af386074080423aec34695etokenizer.model:
0823f5b9133c68a8140addc5d7a425fa9119c4c8cb4a550363b4bffa4ba1c8c7Use the strict Needle Point runtime and provide a finite candidate-tool set for each request. The model is not intended to authorize tools or bypass runtime policy checks.