raducius/Llama-3.1-8B-Instruct-LLM2Vec-mntp-merged

Llama-3.1-8B-Instruct-LLM2Vec-mntp-merged

Built with Llama.

Text-embedding encoder used by the Kimodo Animation Maker (Houdini AI Assistant): LLM2Vec MNTP adaptation of Llama-3.1-8B-Instruct, with the McGill-NLP adapters merged into the base weights for direct loading. Produces one pooled 4096-dim embedding per text prompt, consumed by the Kimodo motion-generation models.

This repository exists so the Kimodo installer can fetch the encoder automatically. It is not a chat model.

License and attribution

Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All rights reserved. Use of this model is subject to that license and to Meta's Acceptable Use Policy. This model is a derivative of meta-llama/Llama-3.1-8B-Instruct; per the license, the model name begins with "Llama".

LLM2Vec adapters: © McGill NLP, MIT license (McGill-NLP/LLM2Vec-Meta-Llama-31-8B-Instruct-mntp and -supervised).