Chronos-Gold-12B-1.0-GGUF

QuantFactory/Chronos-Gold-12B-1.0-GGUF

This is quantized version of elinas/Chronos-Gold-12B-1.0 created using llama.cpp

Original Model Card

Chronos Gold 12B-1.0

Chronos Gold 12B 1.0 is a very unique model that applies to domain 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 model was trained at a sequence length of 16384 (16k) and will still retain the apparent 128k context length from Mistral-Nemo.

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 iterative and objective 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

LlamaCPP

GGUFs from @bartowski

Exllama2

4.5bpw by @Pyroserenus

5.5bpw by @Pyroserenus

6.5bpw by @Pyroserenus

8.0bpw by @Pyroserenus

FP8

FP8 Quant by @Pyroserenus

Sampling Settings

Nemo is a bit sensitive to high temperatures, so I use lower. Here are my settings:

Temp - 0.7 (0.9 max)
Presence Penalty - 1.0
Repetition Penalty range - 2800
Min P - 0.10

Additional Details

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.