Instructions to use redrix/GodSlayer-12B-ABYSS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use redrix/GodSlayer-12B-ABYSS with Transformers:

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

pipe = pipeline("text-generation", model="redrix/GodSlayer-12B-ABYSS")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("redrix/GodSlayer-12B-ABYSS")
model = AutoModelForCausalLM.from_pretrained("redrix/GodSlayer-12B-ABYSS")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use redrix/GodSlayer-12B-ABYSS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "redrix/GodSlayer-12B-ABYSS"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redrix/GodSlayer-12B-ABYSS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/redrix/GodSlayer-12B-ABYSS

SGLang

How to use redrix/GodSlayer-12B-ABYSS 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 "redrix/GodSlayer-12B-ABYSS" \
    --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": "redrix/GodSlayer-12B-ABYSS",
		"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 "redrix/GodSlayer-12B-ABYSS" \
        --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": "redrix/GodSlayer-12B-ABYSS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use redrix/GodSlayer-12B-ABYSS with Docker Model Runner:
```
docker model run hf.co/redrix/GodSlayer-12B-ABYSS
```

Feedback: Love it

by jarnMod - opened Jul 4, 2025

Discussion

jarnMod

Jul 4, 2025

Dear Redrix, thank you for such amazing model.
I've tried a few of your models, including the Angel Slayer, and I find this one to be better, at similar preset. So far, the respond is good. It follows character cards well. It drives plot. It picks up context fine. Best thing about it is it doesn't break with big context. I use it on Agnestic on local Ollama. My prompt was like 2MB and it still function really well.

There has been one strange respond so far, but it's LLM so I'm not going to cry about it. I think it might be interesting, however. The respond ended like this:
[normal respond] You have reached your usage limit. Please refill your credit before continue.

By the way, I use 8bit Quantization version because my GPU can't run Crysis. The model works with good performance and I have nothing but praise. Thank you.

redrix

Owner Oct 2, 2025

Thanks for your feedback. Sorry for my belated reply — I've been off HF for the past few months due to life business.

Indeed, I've been using GodSlayer as my main driver since I created it. I agree with your feedback, sometimes it spouts random administrative garbage. But it's rare and easily deleted, and sometimes interesting and helpful. I've a lot of catching-up to do with the scene, but I want to expand upon this model's performance at some point.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment