Native GGML/GGUF text encoder 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:

The downloader installs the recommended Q8_0 variant by default. Select a different one with --text-quantization bf16|q8_0|q6_k|q5_k|q4_k|q4_k_m. Every variant is one monolithic weight GGUF and uses the same tokenizer.gguf. Kimodo reads individual tensor ranges from the monolith, so streaming one layer at a time does not require separate per-layer files.

The legacy split BF16 tree remains temporarily available for older clients.

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 every published artifact, plus the weight/tokenizer mapping for each quantization.