# Uncensored Dialogue

Veritas-12B is a 12-billion-parameter large language model focused on philosophical reasoning and logical analysis, excelling in handling complex ethical dilemmas and philosophical dialogues.

Veritas-12B is a 12-billion-parameter large language model specializing in philosophical reasoning and logical rigor, excelling in handling complex ethical dilemmas and philosophical dialogues.

This is a distilled model based on Llama-70B, converted to MLX format via mlx-lm and quantized to 4 bits.

Llamacpp imatrix quantized version based on the Qwen2.5-Coder-1.5B-Instruct-abliterated model, suitable for code generation and text generation tasks.

Phi-3.5-mini-instruct_Uncensored is a quantized language model suitable for use under various hardware conditions.

This is an orthogonalized version of microsoft/Phi-3-medium-4k-instruct, where specific techniques suppress the model's tendency to reject, preserving as much of the original model's knowledge and capabilities as possible.

A cybersecurity-specific model fine-tuned based on Cerebras-GPT-6.7B, with basic conversational capabilities

StarChat-β is a language model fine-tuned based on StarCoderPlus, focusing on programming assistance tasks and supporting 80+ programming languages

The 30B-Lazarus Model is an experimental language model that applies LoRA and model fusion, aiming to enhance model characteristics through superposition while avoiding feature dilution effects.