Work in progress. Vectors will be uploaded as they're created.

Available

• optimism_vs_nihilism
• humility_vs_narcissism
• language (simple vs ornate)

Coming soon
compassion_vs_sadism, empathy_vs_sociopathy, honesty_vs_machiavellianism, character focus (dialogue_vs_narration), storytelling (descriptive vs explicit)

gghfez/MiMo-V2.6-Pro-RL-control-vectors

Creative Writing control-vectors for XiaomiMiMo/MiMo-V2.6-Pro-RL

Write a single HTML file with a full-page canvas and no libraries. Simulate a realistic side-view of a moving car as the main subject. Keep the car visible in the foreground while the background landscape scrolls continuously to create the feeling that the car is driving forward. Use layered scenery for depth: nearby ground, roadside elements, trees, poles, and distant hills or mountains should move at different speeds for a natural parallax effect. Animate the wheels spinning realistically and add subtle body motion so the car feels connected to the road. Let the environment pass smoothly behind it, with repeating but varied scenery that makes the movement feel believable. Use cinematic lighting and a cohesive sky, such as sunset, dusk, or daylight, to enhance atmosphere. The overall motion should feel calm, immersive, and realistic, with a seamless looping animation.

What are Control Vectors?

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.

Available Vectors

• optimism_vs_nihilism

Work in progress

• compassion_vs_sadism
• empathy_vs_sociopathy
• honesty_vs_machiavellianism
• humility_vs_narcissism
• character focus (dialogue_vs_narration)
• language (simple vs ornate)
• storytelling (descriptive vs explicit)

Usage

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!

Examples (ik_llama.cpp or llama.cpp)

At server start-up

llama-server --model MiMo-V2.6-Pro-RL-Q8_0.gguf [your usual CLI arguments] \
    --control-vector-scaled MiMo-V2.6-Pro-RL_optimism_vs_nihilism__debias.gguf:1.0 \
    --control-vector-scaled MiMo-V2.6-Pro-RL_optimism_vs_nihilism__nihilism.gguf:1.0 \

Load via API (ik_llama.cpp only)

load direction vector

curl 'http://127.0.0.1:8080/control-vectors/load' \
  -X POST \
  --data-raw '{"path":"/path/to/MiMo-V2.6-Pro-RL-control-vectors/MiMo-V2.6-Pro-RL_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/MiMo-V2.6-Pro-RL-control-vectors/MiMo-V2.6-Pro-RL_optimism_vs_nihilism__debias.gguf","scale":1}'

check loaded control-vectors

curl http://127.0.0.1/control-vectors

Samples

UI theme / SVG generation steering

Concepts from these control-vectors apply across multiple domains. Here is an example of 3 SVGs generated with the same prompt
Prompt

System: You are a helpful assistant.

User: create an svg of a cat.

Writing Steering

Prompt

TODO

TODO

TODO

TODO

Acknowledgements

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!