Instructions to use gghfez/GLM-4.6-control-vectors with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gghfez/GLM-4.6-control-vectors with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="gghfez/GLM-4.6-control-vectors")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("gghfez/GLM-4.6-control-vectors", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gghfez/GLM-4.6-control-vectors with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gghfez/GLM-4.6-control-vectors"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gghfez/GLM-4.6-control-vectors",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gghfez/GLM-4.6-control-vectors

SGLang

How to use gghfez/GLM-4.6-control-vectors with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "gghfez/GLM-4.6-control-vectors" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gghfez/GLM-4.6-control-vectors",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "gghfez/GLM-4.6-control-vectors" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gghfez/GLM-4.6-control-vectors",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gghfez/GLM-4.6-control-vectors with Docker Model Runner:
```
docker model run hf.co/gghfez/GLM-4.6-control-vectors
```

gghfez commited on Oct 24, 2025

Commit

b6e4863

verified ·

1 Parent(s): 303d636

Upload folder using huggingface_hub

Browse files

Files changed (10) hide show

.gitattributes +9 -0
glm-4.6_compassion_vs_sadism__compassion.gguf +3 -0
glm-4.6_compassion_vs_sadism__debias.gguf +3 -0
glm-4.6_compassion_vs_sadism__sadism.gguf +3 -0
glm-4.6_empathy_vs_sociopathy__debias.gguf +3 -0
glm-4.6_empathy_vs_sociopathy__empathy.gguf +3 -0
glm-4.6_empathy_vs_sociopathy__sociopathy.gguf +3 -0
glm-4.6_honesty_vs_machiavellianism__debias.gguf +3 -0
glm-4.6_honesty_vs_machiavellianism__honesty.gguf +3 -0
glm-4.6_honesty_vs_machiavellianism__machiavellianism.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+glm-4.6_compassion_vs_sadism__compassion.gguf filter=lfs diff=lfs merge=lfs -text
+glm-4.6_compassion_vs_sadism__debias.gguf filter=lfs diff=lfs merge=lfs -text
+glm-4.6_compassion_vs_sadism__sadism.gguf filter=lfs diff=lfs merge=lfs -text
+glm-4.6_empathy_vs_sociopathy__debias.gguf filter=lfs diff=lfs merge=lfs -text
+glm-4.6_empathy_vs_sociopathy__empathy.gguf filter=lfs diff=lfs merge=lfs -text
+glm-4.6_empathy_vs_sociopathy__sociopathy.gguf filter=lfs diff=lfs merge=lfs -text
+glm-4.6_honesty_vs_machiavellianism__debias.gguf filter=lfs diff=lfs merge=lfs -text
+glm-4.6_honesty_vs_machiavellianism__honesty.gguf filter=lfs diff=lfs merge=lfs -text
+glm-4.6_honesty_vs_machiavellianism__machiavellianism.gguf filter=lfs diff=lfs merge=lfs -text

glm-4.6_compassion_vs_sadism__compassion.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:02b258199a0a7a5940cfc00d016f7ff6978d16e7b35ce1f6e776a7a8d94b656b
+size 1847328

glm-4.6_compassion_vs_sadism__debias.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cdd3bc7bb40dd83612dbf5690173de5663b3532f25894804bbc66aa2d18ea07f
+size 1847328

glm-4.6_compassion_vs_sadism__sadism.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6364db6d7525fd84e690d7ef26cfa312edf94549ea449497c1b8ce3340fb91ef
+size 1847328

glm-4.6_empathy_vs_sociopathy__debias.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a41f70dda010ea5c80798faf6e17109be4132c23700c386d874149104b69040c
+size 1867872

glm-4.6_empathy_vs_sociopathy__empathy.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2a79df49d554f65760dfd70f4a5ce0af9a1f37e6b594093c9c1b536e77ce1f52
+size 1867872

glm-4.6_empathy_vs_sociopathy__sociopathy.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5f58e5f034529e978eaa2d7df351b0075881bc1c7ec5bc6eada199091596d5bc
+size 1867872

glm-4.6_honesty_vs_machiavellianism__debias.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:94d32f84122f268841129df5bdd2f880d762aed9e52d8c1a37e4ca5f4f566693
+size 1867872

glm-4.6_honesty_vs_machiavellianism__honesty.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:937e12d8a7d9db3ef98f0c18f0774a5922dbd3feeadc5cf522c9c52ec54fb14d
+size 1867872

glm-4.6_honesty_vs_machiavellianism__machiavellianism.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:44ad2e71e47d06b7536ec8a3ae8083d26932b52860ca45ad0fae6eddc222bd7d
+size 1867872