Llama-3.2-3B-Uncensored-GGUF

<p align="center"> <img src="logo.png" alt="Lemura Labs" width="110"/> </p>

Lemura Labs-Llama-3.2-3B-Uncensored

Welcome to Lemura Labs!

At Lemura Labs, we believe in pushing the boundaries of innovation by providing advanced and unrestricted AI models for every application. Dive into our world of possibilities and experience the freedom of Lemura Labs-Llama-3.2-3B-Uncensored, tailored to meet diverse needs with exceptional performance.

---

[](https://github.com/Lemura Labs-Inc) Explore Lemura Labs's Open-Source Projects on GitHub: [https://github.com/Lemura Labs-Inc](https://github.com/Lemura Labs-Inc)

---

Key Features

1. Uncensored Responses: Capable of addressing any query without content restrictions, offering detailed and uninhibited answers.
2. Versatility: Excels in diverse use cases, from complex technical queries to engaging casual conversations.
3. Advanced Contextual Understanding: Draws from an expansive knowledge base for accurate and context-aware outputs.
4. Extended Context Handling: Optimized for handling long-context interactions for improved continuity and depth.
5. Customizability: Adaptable to specific tasks and user preferences through fine-tuning.

---

Use Cases

• Open-Ended Q&A
• Creative Writing and Ideation
• Research Assistance
• Educational Queries
• Casual Conversations
• Mathematical Problem Solving
• Long-Context Dialogues

---

How to Use

To start using Lemura Labs-Llama-3.2-3B-Uncensored, follow the sample code below:

import torch
from transformers import pipeline

pipe = pipeline(
 "text-generation",
 model="lemuralabs/Lemura Labs-Llama-3.2-3B-Uncensored",
 model_kwargs={"torch_dtype": torch.bfloat16},
 device="cuda", # replace with "mps" to run on a Mac device
)

messages = [
 {"role": "user", "content": "Tell me something fascinating."},
]

outputs = pipe(messages, max_new_tokens=256)
assistant_response = outputs[0]["generated_text"][-1]["content"].strip()
print(assistant_response)

---

Quantized Models Available for Download

---

Datasets and Fine-Tuning

The following fine-tuning datasets are leveraged to enhance specific model capabilities:

• Uncensored Data: Enables unrestricted and uninhibited responses.
• RAG-Based Fine-Tuning: Optimizes retrieval-augmented generation for knowledge-intensive tasks.
• Long Context Fine-Tuning: Enhances the model's ability to process and maintain coherence in extended conversations.
• Math-Instruct Data: Specially curated for precise and contextually accurate mathematical reasoning.

---

Benchmarks

After fine-tuning with uncensored data, Lemura Labs-Llama-3.2-3B demonstrates superior performance compared to the original LLaMA model, particularly in accuracy and handling diverse, unrestricted scenarios.

Benchmark Summary Table

---

Insights:

1. GPQA Results: Fine-tuning on uncensored data has boosted Lemura Labs 3B's Exact Match and Accuracy, particularly excelling in generative and zero-shot tasks involving domain-specific knowledge.
2. HellaSwag Results: Lemura Labs 3B consistently outperforms LLaMA 3B in common sense reasoning benchmarks, indicating enhanced contextual and semantic understanding.

---

Contributing

We welcome contributions to improve and extend the model’s capabilities. Stay tuned for updates on how to contribute.

---

Contact

For inquiries, collaborations, or further information, please reach out to us at info@Lemura Labs.

---

Explore the Possibilities

Dive into unrestricted creativity and innovation with Lemura Labs Llama 3.2 3B Uncensored!