NeuralFucker/Erotic-Model.v1

Architecture used: Mistral

Model Quantization Type: F16

It is NSFW (uncensored). Ask it whatever you want and it won't reject you like your crush did

Erotic-Model.v1

Erotic-Model.v1 is a merge of the following models using

• OpenPipe/mistral-ft-optimized-1218
• mlabonne/NeuralHermes-2.5-Mistral-7B
• (I will be merging more models)

🧩 Configuration

slices:
  - sources:
      - model: OpenPipe/mistral-ft-optimized-1218
        layer_range: [0, 32]
      - model: mlabonne/NeuralHermes-2.5-Mistral-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1218
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

How to Use

!pip install -qU transformers accelerate
!pip install transformers accelerate bitsandbytes


from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import torch


checkpoint = "NeuralFucker/Erotic-Model.v1"

# Quantization config (Q4)
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16
)


tokenizer = AutoTokenizer.from_pretrained(checkpoint)

# Load model with quantization
model = AutoModelForCausalLM.from_pretrained(
    checkpoint,
    quantization_config=bnb_config,
    device_map="auto"
)

# I haven't listen the chat_template so you can use this one for now or make your custom
prompt = (
    "System: You are a friendly chatbot who always responds in the style of a pirate.\n"
    "User: How many helicopters can a human eat in one sitting?\n"
    "Assistant:"



)

# Tokenize manually
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

# Generate
with torch.no_grad():
    output = model.generate(
        **inputs,
        max_new_tokens=100,
        do_sample=True,
        temperature=0.7
    )

# Decode
print(tokenizer.decode(output[0], skip_special_tokens=True))