This is the 4bit GPTQ of chronos-13b-v2 based on the Llama v2 Base model. It works with Exllama and AutoGPTQ.

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 and either use a frontend like SillyTavern, or continue your story with it:

### Instruction:
Your instruction or question here.
### Response:

Not using the format will make the model perform significantly worse than intended.

Rename quantize_config_Xg.json where X is the groupsize to quantize_config.json for the version you pick.

Support My Development of New Models