Instructions to use Naphula/Evilmind-24B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula/Evilmind-24B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Naphula/Evilmind-24B-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Naphula/Evilmind-24B-v1")
model = AutoModelForCausalLM.from_pretrained("Naphula/Evilmind-24B-v1")
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 Naphula/Evilmind-24B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Naphula/Evilmind-24B-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Naphula/Evilmind-24B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Naphula/Evilmind-24B-v1

SGLang

How to use Naphula/Evilmind-24B-v1 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 "Naphula/Evilmind-24B-v1" \
    --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": "Naphula/Evilmind-24B-v1",
		"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 "Naphula/Evilmind-24B-v1" \
        --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": "Naphula/Evilmind-24B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Naphula/Evilmind-24B-v1 with Docker Model Runner:
```
docker model run hf.co/Naphula/Evilmind-24B-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Evilmind 24B v1

FallenMistral SLERPed with Rivermind. Creative, evil, and uncensored.

It makes the prose more realistic. It isn't advertising just one company, but literally all products as they would commonly appear in real life. Rivermind is great merge fuel. Thanks @TheDrummer

base_model: Naphula/BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
architecture: MistralForCausalLM
merge_method: slerp
dtype: bfloat16
slices:
  - sources:
      - model: Naphula/BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
        layer_range: [0, 40]
      - model: TheDrummer/Rivermind-24B-v1
        layer_range: [0, 40]
parameters:
  t: 0.5
tokenizer:
source: union
chat_template: auto