Instructions to use byroneverson/glm-4-9b-chat-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use byroneverson/glm-4-9b-chat-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="byroneverson/glm-4-9b-chat-abliterated", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("byroneverson/glm-4-9b-chat-abliterated", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use byroneverson/glm-4-9b-chat-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "byroneverson/glm-4-9b-chat-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": "byroneverson/glm-4-9b-chat-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/byroneverson/glm-4-9b-chat-abliterated

SGLang

How to use byroneverson/glm-4-9b-chat-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 "byroneverson/glm-4-9b-chat-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": "byroneverson/glm-4-9b-chat-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 "byroneverson/glm-4-9b-chat-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": "byroneverson/glm-4-9b-chat-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use byroneverson/glm-4-9b-chat-abliterated with Docker Model Runner:
```
docker model run hf.co/byroneverson/glm-4-9b-chat-abliterated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

glm-4-9b-chat-abliterated

Version 1.1 (Updated 9/1/2024): Layer 16 is used for abliteration instead of 20. Refusal mitigation tends to work better with this layer. PCA and cosine similarity tests seem to agree.

Check out the jupyter notebook for details of how this model was abliterated from glm-4-9b-chat.

The python package "tiktoken" is required to quantize the model into gguf format. So I had to create a fork of GGUF My Repo (+tiktoken).

Downloads last month: 185

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for byroneverson/glm-4-9b-chat-abliterated

Base model

zai-org/glm-4-9b-chat

Finetuned

(10)

this model

Quantizations

5 models