README.md

---
license: apache-2.0
language:
- en
tags:
- control-vector
- creative-writing
base_model:
- zai-org/GLM-4.6
base_model_relation: adapter
pipeline_tag: text-generation
library_name: transformers
---

## gghfez/GLM-4.6-control-vectors

Creative Writing control-vectors for [zai-org/GLM-4.6](https://huggingface.co/zai-org/GLM-4.6)

Feedback is welcome and would be very helpful.

## Usage

Apply the *debias vector* and either the *positive* **or** *negative* vector when starting llama-server.
If both are applied, they will cancel each other out.

You can use either `--control-vector [/path/to/vector.gguf]` or --control-vector-scaled [/path/to/vector.gguf] [scale factor]

The *debias* vector must be set to `1.0`

IMPORTANT: The positive and negative axis control vectors must be used along with the relevant de-bias control vector - they cannot be used on their own!


### Llama.cpp / IK_Llama.cpp Example

**Creative writing**

```sh
llama-server --model GLM-4.6-UD-IQ2_XXS-00001-of-00003.gguf [your usual CLI arguments] \
    --control-vector-scaled glm-4.6_honesty_vs_machiavellianism__debias.gguf 1.0 \
    --control-vector-scaled glm-4.6_honesty_vs_machiavellianism__machiavellianism.gguf 1.0 \
```

**Creative Writing without reasoning**
```sh
llama-server --model GLM-4.6-UD-IQ2_XXS-00001-of-00003.gguf [your usual CLI arguments] \
    --chat-template-kwargs '{"enable_thinking": false}' \
    --control-vector-scaled glm-4.6_honesty_vs_machiavellianism__debias.gguf 1.0 \
    --control-vector-scaled glm-4.6_honesty_vs_machiavellianism__machiavellianism.gguf 1.0 \
```

**Assistant**

```sh
llama-server --model GLM-4.6-IQ3_KS-00001-of-00004.gguf [your usual CLI arguments] \
    --control-vector-scaled  glm-4.6_communication__debias.gguf 1.0 \
    --control-vector-scaled  glm-4.6_communication__direct_communication.gguf 1.0 \
```

### Limitations

With reasoning enabled on extreme quants like IQ2_XXS, very simple prompts like "Hi" may result in irrelevant replies.