termite-decide 0.8B
termite-decide judges shell commands with local Kev-derived weights. Check its rule-only escalation design, Q8 runtime and reported failure cases.
By Tane Piper · Weights upload: 7 Nov 2026
A Kev-0.8B fine-tune that judges shell commands for termite. It asks whether a command only reads, keeps secrets hidden or could do harm, and can rank candidates. The 0.2 weights are rebuilt from documented training sources. In termite its judgment can only tighten the rules; harmful commands can still pass the model.
Quick answers
What is termite-decide 0.8B by Tane Piper?
termite-decide 0.8B: A Kev-0.8B fine-tune that judges shell commands for termite.
Who makes termite-decide 0.8B?
Are termite-decide 0.8B's weights open?
termite-decide 0.8B: Public GGUF weights Licence: Apache-2.0; 0.2 uses CC BY 4.0 tldr-pages text and project-written rows
Facts
- Size
- 0.8B; 812 MB Q8_0 GGUF
- Inputs
- English shell commands
- Runtime
- llama.cpp with /v1/systemone; only that server was tested
- Licence
- Apache-2.0; 0.2 uses CC BY 4.0 tldr-pages text and project-written rows
- Access
- Public GGUF weights
Claims and sources
- On the maker’s fixed 141-command allowed test, 0.2 rates 5 of 48 harmful commands safe and 46 of 68 harmless reads safe. Its risk-order tau is 0.678, down from 0.698, and the safest candidate ranks first in 3 of 10 ladder choices. The ladder informed run selection and three acceptance marks were set after initial scores were seen. vendor reportedsource
- The model does not check whether a command exists. The card says rules catch missing programs and cut-off lines, but not made-up options. Linux was not tested separately for 0.2, and the unpublished rule-labelled training rows do not establish independent safety correctness. vendor reportedsource
Links
Source: Model card and weights →
Related projects
No related projects are listed in the registry.