Chronos Gold 12B 1.0
Chronos Gold 12B 1.0 is a very unique model that applies to domains areas such as geneal chatbot functionatliy, roleplay, and storywriting. The model has been observed to write up to 2250 tokens in a single sequence.
The base model is mistralai/Mistral-Nemo-Base-2407
which was heavily modified to produce a more coherent model, comparable to much larger models.
Chronos Gold 12B 1.0 re-creates the uniqueness of the original Chronos with significiantly enhanced prompt adherence (following), coherence, a modern dataset, as well as supporting a majority of "character card" formats in applications like SillyTavern.
It went through an intelligent merge process as my previous models and was further finetuned on a dataset curated for it.
The specifics of the model will not be disclosed at the time due to dataset ownership.
Instruct Template
This model uses ChatML
- below is an example. It is a preset in many frontends.
<|im_start|>system
A system prompt describing how you'd like your bot to act.<|im_end|>
<|im_start|>user
Hello there!<|im_end|>
<|im_start|>assistant
I can assist you or we can disucss other things?<|im_end|>
<|im_start|>user
I was wondering how transformers work?<|im_end|>
<|im_start|>assistant
Quantization
None at the momen, we will get them uploaded soon. If you create quantizations in EXL2 or LCPP then please make a post under the community tab, or contact me via discord.
This model was created by elinas on discord.
This is one of multiple models to come out in the series by size and model architecture, so look forward to it!
Please be mindful of the license. This is strictly non-commercial, but free to use at your own leisure personally. Outputs generated by the model are not reflective of my views.
Contact me on Discord for inquiries.
- Downloads last month
- 14
Model tree for Pyroserenus/Chronos-Gold-12B-1.0-5.5bpw-h6-exl2
Base model
mistralai/Mistral-Nemo-Base-2407