|
--- |
|
license: apache-2.0 |
|
tags: |
|
- mistral |
|
- pytorch |
|
- chatbot |
|
- storywriting |
|
--- |
|
|
|
# Chronos-Mistral-7B |
|
|
|
This is the FP16 PyTorch / HF version of **chronos-mistral-7b** finetuned on the **Mistral v0.1 Base** model. |
|
|
|
**PLEASE NOTE: This is an experimental model, and further iterations will likely be released** |
|
|
|
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 |
|
|
|
**Up to 16384 with RoPE** with solid coherency. |
|
|
|
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 unless it is merged. |
|
|
|
## Other Versions (Quantizations) |
|
|
|
TBD |
|
|
|
|
|
**Support My Development of New Models** |
|
<a href='https://ko-fi.com/Q5Q6MB734' target='_blank'><img height='36' style='border:0px;height:36px;' |
|
src='https://storage.ko-fi.com/cdn/kofi1.png?v=3' border='0' alt='Support Development' /></a> |
|
|