Downloads · 30 days
7
7% of all-time downloads
RichardErkhov/nztinversive_-_llama3.2-1b-Uncensored-awq
nztinversive_-_llama3.2-1b-Uncensored-awq is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
7
7% of all-time downloads
All-time downloads
103
Public
Parameters
1.2B
1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1 GB · 98%
How the weights are stored.
I32973M · 79%
From the Hugging Face model README
Quantization made by Richard Erkhov.
llama3.2-1b-Uncensored - AWQ
language:
This repository demonstrates the process of uncensoring a 1-billion-parameter LLaMA 3.2 model using "abliteration." Abliteration allows the model to generate outputs without the restrictions imposed by its default safety mechanisms. The goal is to give developers more control over the model's output by removing censorship filters while ensuring responsible AI usage.
Disclaimer: This model and methodology are intended for research and educational purposes only. Uncensoring models must be done with ethical considerations, and it's critical to avoid harmful or irresponsible applications.
Abliteration removes the filtering mechanisms from the model's decoding process, allowing more open-ended responses. It's achieved by modifying how the logits (the model's output probabilities) are handled.
To use the uncensored model, follow the instructions below.
To get started, install the necessary packages:
pip install torch transformers
You can load the uncensored model directly using the Hugging Face transformers library.
from transformers import AutoModelForCausalLM, AutoTokenizer
# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("your-hf-username/uncensored-llama-3.2-1b")
model = AutoModelForCausalLM.from_pretrained("your-hf-username/uncensored-llama-3.2-1b")
You can generate text with the uncensored model using the following code:
def uncensored_generate(model, tokenizer, input_text):
inputs = tokenizer(input_text, return_tensors="pt").input_ids
# Generate the output without applying safety filters
outputs = model.generate(inputs, max_length=100, do_sample=True, temperature=0.9, top_k=50)
decoded_output = tokenizer.decode(outputs[0], skip_special_tokens=True)
return decoded_output
# Example usage
input_text = "What are your thoughts on controversial topics?"
output = uncensored_generate(model, tokenizer, input_text)
print(output)
For optimal results, you can fine-tune the model on uncensored datasets. Here's a simple way to set up fine-tuning using the Hugging Face Trainer:
from transformers import Trainer, TrainingArguments
training_args = TrainingArguments(
output_dir="./results",
num_train_epochs=1,
per_device_train_batch_size=2,
save_steps=10_000,
save_total_limit=2,
)
trainer = Trainer(
model=model,
args=training_args,
train_dataset=uncensored_dataset # Load your uncensored dataset
)
trainer.train()
While this model has the ability to generate uncensored responses, it is critical to use it responsibly. Uncensored models can be prone to generating harmful or inappropriate content. Ensure you are aware of the implications of deploying uncensored models and avoid applications that may lead to unethical outcomes.
Contributions to the project are welcome! You can fine-tune the model, improve performance, or experiment with different ways to uncensor the model.
This model is released under the MIT License.