Naive-N0.5-Flash-NVFP4 / runtime /THIRD_PARTY_NOTICES.md
piotrkosecki's picture
Add tested native vLLM TP4 runtime, RTX PRO instructions and validation
36e36f3 verified
|
Raw History Blame Contribute Delete
843 Bytes
# Licensing and attribution
The quantized model is derived from Naive AI's `Naive-N0.5-Flash` checkpoint.
Its MIT license and copyright notice are preserved in the repository's root
`LICENSE` file. Naive AI describes the original model as a derivative of
Xiaomi MiMo-V2.5; see the linked upstream model card for that lineage.
The upstream `configuration_naive_n05_flash.py` and
`modeling_naive_n05_flash.py` retain their original Apache-2.0 copyright and
license headers. The Apache-2.0 license text is in `LICENSE-APACHE-2.0.txt`.
The additional runtime scripts and deployment files in `runtime/`, and the
root `compose.yml`, are provided under the MIT terms in `runtime/LICENSE`.
Dependencies downloaded during the Docker build retain their own licenses;
the dependency image and Python packages are not redistributed in this
repository.