license: other | |
language: | |
- en | |
pipeline_tag: text-generation | |
inference: false | |
tags: | |
- transformers | |
- gguf | |
- imatrix | |
- chronos-13b-v2 | |
Quantizations of https://huggingface.co/elinas/chronos-13b-v2 | |
# From original readme | |
This is the FP16 PyTorch / HF version of **chronos-13b-v2** based on the **LLaMA v2 Base** model. | |
Only use this version for further quantization or if you would like to run in full precision, as long as you have the VRAM required. | |
This model is primarily focused on chat, roleplay, storywriting, with good reasoning and logic. | |
Chronos can generate very long outputs with coherent text, largely due to the human inputs it was trained on, and it supports context length up to 4096 tokens. | |
This model uses Alpaca formatting, so for optimal model performance, use it to start the dialogue or story, and if you use a frontend like SillyTavern ENABLE instruction mode: | |
``` | |
### Instruction: | |
Your instruction or question here. | |
### Response: | |
``` | |
Not using the format will make the model perform significantly worse than intended. |