Chronos Hermes 13B GGUF
| Property | Value |
|---|---|
| Parameter Count | 13B |
| Model Type | LLaMA-based |
| License | Other |
| Author | TheBloke (Quantized) / Austism (Original) |
What is chronos-hermes-13B-GGUF?
Chronos Hermes 13B GGUF is a sophisticated language model that combines the creative storytelling capabilities of Chronos-13B with the instruction-following prowess of Nous-Hermes-13B in a 75/25 merge ratio. This model has been specifically optimized for generating detailed, coherent narratives while maintaining strong adherence to user instructions.
Implementation Details
The model is available in various GGUF quantization formats, ranging from 2-bit to 8-bit precision, allowing users to balance between model size and performance. The recommended Q4_K_M variant offers an optimal balance of quality and resource usage at 7.87GB.
- Multiple quantization options from Q2_K (5.43GB) to Q8_0 (13.83GB)
- Supports GPU layer offloading for optimized performance
- Uses the Alpaca prompt template format
- Compatible with llama.cpp and various third-party UIs
Core Capabilities
- Enhanced narrative generation and storytelling
- Improved instruction following compared to base Chronos
- Long-form, descriptive output generation
- Coherent and contextually appropriate responses
- Balanced creative writing with logical structure
Frequently Asked Questions
Q: What makes this model unique?
This model uniquely combines Chronos's descriptive and creative writing capabilities with Hermes's improved instruction-following abilities, resulting in a more controlled yet creative language model ideal for narrative tasks.
Q: What are the recommended use cases?
The model excels at creative writing, storytelling, and generating detailed descriptive content. It's particularly well-suited for narrative-driven applications where both creativity and coherence are essential.
