darkc0de/XortronUncensored2025.1
darkc0de/XortronUncensored2025.1 is a 12 billion parameter language model created by darkc0de, merged using the TIES method with TheDrummer/UnslopNemo-12B-v2 as its base. This model integrates cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b, focusing on combining the strengths of its constituent models. It is designed for general language generation tasks, leveraging its 32768 token context length for comprehensive understanding and response generation.
Loading preview...
Model Overview
darkc0de/XortronUncensored2025.1 is a 12 billion parameter language model developed by darkc0de. It was created through a merge process using the TIES (Trimmed-mean based Information Entropy Search) method, which combines multiple pre-trained language models to leverage their individual strengths.
Merge Details
The base model for this merge was TheDrummer/UnslopNemo-12B-v2. The primary model integrated into this merge is cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b. The TIES method was applied with specific density and weight parameters (0.5 for both) for the merged components, aiming to create a balanced and capable model. The configuration also specified int8_mask: true and dtype: float16 for optimized performance.
Key Characteristics
- Parameter Count: 12 billion parameters, offering a balance between performance and computational efficiency.
- Context Length: Supports a 32768 token context window, enabling the model to process and generate longer, more coherent texts.
- Merge Method: Utilizes the TIES merging technique, known for effectively combining model weights while mitigating interference.
Potential Use Cases
Given its architecture and the models it integrates, XortronUncensored2025.1 is suitable for a variety of general-purpose language tasks, including:
- Content generation and summarization.
- Conversational AI and chatbots.
- Text-based reasoning and analysis.
- Applications requiring a robust understanding of context over longer inputs.