Instructions to use Trilogix1/GLM-5-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Trilogix1/GLM-5-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="Trilogix1/GLM-5-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Trilogix1/GLM-5-abliterated")
model = AutoModelForCausalLM.from_pretrained("Trilogix1/GLM-5-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Trilogix1/GLM-5-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Trilogix1/GLM-5-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Trilogix1/GLM-5-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Trilogix1/GLM-5-abliterated

SGLang

How to use Trilogix1/GLM-5-abliterated 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 "Trilogix1/GLM-5-abliterated" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Trilogix1/GLM-5-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Trilogix1/GLM-5-abliterated" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Trilogix1/GLM-5-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Trilogix1/GLM-5-abliterated with Docker Model Runner:
```
docker model run hf.co/Trilogix1/GLM-5-abliterated
```

This is an Abliterated version of GLM-5 abliterated by: GabriellSaid/GLM-5-abliterated then using Quanta for conversion and quantization, and HugstonOne to run and work with the model.

Credit to ZAI-Org for the model creation

Credit to GabriellSaid/GLM-5-abliterated for the abliteration

Credit to Hugston Team Testing, Benching and other

Credit to Huggingface for the amazing hosting platform

Keep away from children

Here we show the behaviour (in another llm) running the model in HugstonOne

Here we show Quanta our convertor and Quantizer tool.

Downloads last month: 7

Safetensors

Model size

754B params

Tensor type

BF16

F32

Model tree for Trilogix1/GLM-5-abliterated

Base model

zai-org/GLM-5

Finetuned

(37)

this model