monster/kimodo-mrp.ccc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
e55a42aaa3
kimodo-mrp.ccc/scripts/hf/Llama-3-Kimodo-GGML/README.md
Richard Palethorpe e55a42aaa3 Make Linux setup primary in documentation
2026-08-23 14:55:36 +01:00

1.1 KiB
Raw Blame History

license library_name tags
other ggml
gguf
ggml
llama-3
text-embeddings

Llama-3-Kimodo-GGML

Native F32 GGML/GGUF text-encoder components used by Kimodo. This is the reusable LLM2Vec encoder only; download a matching Kimodo diffusion model separately, for example Kimodo-SMPLX-RP-v1-GGML.

From a kimodo.cpp checkout with the Hugging Face CLI installed, install both with:

scripts/download_gguf_weights.sh --output "$PWD"

The components intentionally remain split into individual layers so kimodo.cpp can bound GPU memory use while evaluating the encoder.

Provenance and licence

The bundle is converted from Meta Llama-3-8B-Instruct and the MIT-licensed McGill LLM2Vec MNTP and supervised adapters. Built with Meta Llama 3.

LICENSE-META-LLAMA-3.txt and NOTICE accompany this distribution. Review the Meta Llama 3 Community License before use or redistribution. MANIFEST.json records the exact source commits and SHA-256 of each component.