Hydra Nano · Files head

This head is served by Hydra Nano. Download and run that model. The weights stored in this repository are an earlier shared checkpoint that the Hydra installer no longer uses. They are kept so that old links and revisions keep working.

Finds where a symbol is defined and used, ranking definitions above imports, tests and generated or archived copies.

The files head is part of Hydra, a CLI that a coding agent calls instead of running noisy commands itself. The model picks from a fixed, read-only menu; code runs the command and returns its own output lines.

npx --yes --package=github:rahul05ranjan/hydra hydra-install
hydra ask --head files "where is parseConfig defined?"

Evaluation (Hydra Nano v2, Q8_0 GGUF)

Set Solved
Development 192/200 (96.0%)
Held-out 980/1,000 (98.0%)

Real CPython 3.13.5, Node.js 22.16.0, Go 1.24.4 and Rust 1.88.0 sources. The model chooses search terms; ripgrep and code do the search.

A task counts as solved only when every expected fact is returned and nothing forbidden is. Development, held-out and training data are separate. See the Hydra Nano model card for the evaluation method, the training history, the other heads and the limitations.

License

Apache 2.0

Downloads last month
372
Safetensors
Model size
0.9B params
Tensor type
F32
·
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for rahul05ranjan/hydra-nano-files

Finetuned
(4)
this model