Downloads · 30 days
745
100% of all-time downloads
gghfez/MiniMax-M3-control-vectors
MiniMax-M3-control-vectors is a text generation model from gghfez. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
Downloads · 30 days
745
100% of all-time downloads
All-time downloads
745
Public
Repo size
29.5 MB
Likes
3
Public
Click a slice to open those files.
.gguf29.5 MB · 100%
From the Hugging Face model README
TODO
Creative Writing control-vectors for MiniMaxAI/MiniMax-M3
Control vectors steer model behavior without retraining by adjusting activations in specific directions.
These creative writing vectors help you tune narrative tone, character focus, and stylistic elements.
optimism_vs_nihilismempathy_vs_sociopathyhonesty_vs_machiavellianismhumility_vs_narcissismcharacter focus (dialogue_vs_narration)language (simple vs ornate)storytelling (descriptive vs explicit)Apply the debias vector and either the positive or negative vector when starting llama-server.
If both axes are applied at the same time, they will cancel each other out.
The debias vector must be set to 1.0
You can use either --control-vector [/path/to/vector.gguf] or --control-vector-scaled [/path/to/vector.gguf] [scale factor]
When using ik_llama.cpp, you can also use the REST-API (examples below)
IMPORTANT: As these vectors are calibrated against the debiased model, the debias vector must be applied along with the corresponding positive or negative axis control vector - they cannot be used on their own!
At server start-up
llama-server --model MiniMax-M3-Q8_0.gguf [your usual CLI arguments] \
--control-vector-scaled MiniMax-M3-optimism_vs_nihilism__debias.gguf 1.0 \
--control-vector-scaled MiniMax-M3-optimism_vs_nihilism__nihilism.gguf 1.0 \
At server start-up with thinking disabled
llama-server --model MiniMax-M3-Q8_0.gguf [your usual CLI arguments] \
--chat-template-kwargs '{"enable_thinking": false}' \
--control-vector-scaled MiniMax-M3-optimism_vs_nihilism__debias.gguf 1.0 \
--control-vector-scaled MiniMax-M3-optimism_vs_nihilism__nihilism.gguf 1.0 \
load direction vector
curl 'http://127.0.0.1:8080/control-vectors/load' \
-X POST \
--data-raw '{"path":"/path/to/MiniMax-M3-control-vectors/MiniMax-M3-optimism_vs_nihilism__nihilism.gguf","scale":1}'
load debias vector
curl 'http://127.0.0.1:8080/control-vectors/load' \
-X POST \
--data-raw '{"path":"/path/to/MiniMax-M3-control-vectors/MiniMax-M3-optimism_vs_nihilism__debias.gguf","scale":1}'
check loaded control-vectors
curl http://127.0.0.1/control-vectors
TODO
Based on the excellent work and cross-covariance eigendecomposition implementation by @jukofyork. His creative writing control vectors v3.0 repository contains the foundational code and methodology that made this possible, plus 70+ other creative writing control vectors across many models and useful steering directions. Highly recommended for anyone working on improving LLM prose quality!