--- license: apache-2.0 tags: - control vectors - exllamav2 - creative writing - text generation - inference - model integration --- # Creative Writing Control Vectors Integration for ExLlamaV2 This project provides a wrapper to integrate [jukofyork's creative writing control vectors](https://huggingface.co./jukofyork/creative-writing-control-vectors-v3.0) with [ExLlamaV2](https://github.com/turboderp/exllamav2/). While ExLlamaV2 does not natively support control vectors, this wrapper enables loading and injecting GGUF control vectors into the model for dynamic text generation control. ## Overview - Wrapper for using control vectors with ExLlamaV2 - Supports loading control vectors from GGUF format - Injects vectors directly into ExLlamaV2 inference - Enables dynamic text generation control ## Usage 1. Download model in ExLlamaV2 format 2. Create a "-vectors" directory next to model directory 3. Download the control vectors from [jukofyork's repository](https://huggingface.co./jukofyork/creative-writing-control-vectors-v3.0) and place them in the "-vectors" directory. 4. Run inference with the `--control_vectors` (`-vc`) parameter. Example command: ```bash python test_inference.py -m Meta-Llama-3-70B-Instruct-8bpw \ -p "" \ --control_vectors language:simple:0.5,optimism:optimism:0.5 ``` ## Directory Structure Ensure your directory structure follows this format to correctly load the control vectors: ``` models/ ├── Meta-Llama-3-70B-Instruct-8bpw/ │ └── model files... └── Meta-Llama-3-70B-Instruct-8bpw-vectors/ ├── llama-3:70b-language__debias.gguf ├── llama-3:70b-language__simple.gguf ├── llama-3:70b-language__ornate.gguf └── ... ``` ## Limitations - Proof of concept implementation - May impact model performance - Limited testing with different vector combinations - No guarantee of exact equivalence to llama.cpp behavior ## Acknowledgments - Control vectors from [jukofyork's creative-writing-control-vectors-v3.0](https://huggingface.co./jukofyork/creative-writing-control-vectors-v3.0) - [ExLlamaV2 by turboderp](https://github.com/turboderp/exllamav2/)