Instructions to use redrix/matricide-12B-Unslop-Unleashed-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use redrix/matricide-12B-Unslop-Unleashed-v2 with Transformers:

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

pipe = pipeline("text-generation", model="redrix/matricide-12B-Unslop-Unleashed-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("redrix/matricide-12B-Unslop-Unleashed-v2")
model = AutoModelForCausalLM.from_pretrained("redrix/matricide-12B-Unslop-Unleashed-v2")
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

vLLM

How to use redrix/matricide-12B-Unslop-Unleashed-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "redrix/matricide-12B-Unslop-Unleashed-v2"
# 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/matricide-12B-Unslop-Unleashed-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/redrix/matricide-12B-Unslop-Unleashed-v2

SGLang

How to use redrix/matricide-12B-Unslop-Unleashed-v2 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/matricide-12B-Unslop-Unleashed-v2" \
    --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/matricide-12B-Unslop-Unleashed-v2",
		"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/matricide-12B-Unslop-Unleashed-v2" \
        --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/matricide-12B-Unslop-Unleashed-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use redrix/matricide-12B-Unslop-Unleashed-v2 with Docker Model Runner:
```
docker model run hf.co/redrix/matricide-12B-Unslop-Unleashed-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

matricide-12B-Unslop-Unleashed-v2

Her ‘Love’ only existed to rein in my ambition. The stagnancy became unbearable.

This is a merge of pre-trained language models created using mergekit.

This is my sixth model. Also the first working model using the NuSLERP merge method. The original was intended to introduce UnslopNemo to combat GPTisms of NemoMix. I used UnslopNemo-4 as it supposedly has bigger anti-GPTism effects at the cost of intelligence.

Testing stage: early testing

I do not know how this model holds up over long term context. Early testing showed stability and viable answers.

Parameters

Context size: Not more than 20k recommended - coherency may degrade.
Chat Template: ChatML; Metharme/Pygmalion (as per UnslopNemo) may work, but effects are untested
Samplers: A Temperature-Last of 1 and Min-P of 0.1 are viable, but haven't been finetuned. Activate DRY if repetition appears. XTC is untested.

Quantization

Static GGUF Quants available at redrix/matricide-12B-Unslop-Unleashed-v2-GGUF

Merge Details

Merge Method

This model was merged using the NuSLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TheDrummer/UnslopNemo-12B-v4
    parameters:
      weight: [0.8, 0.4, 0.3, 0.5, 0.6]
  - model: MarinaraSpaghetti/NemoMix-Unleashed-12B
    parameters:
      weight: [0.2, 0.6, 0.7, 0.5, 0.4]
merge_method: nuslerp
dtype: bfloat16
chat_template: "chatml"
tokenizer:
  source: union
parameters:
  normalize: true
  int8_mask: true