Chronos Gold 12B-1.0
Chronos Gold 12B 1.0 is a very unique model that applies to domain areas such as general 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, though it deteriorates over time like regular Nemo does based on the RULER Test
As a result, is recommended to keep your sequence length max at 16384, or you will experience performance degredation.
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 discuss other things?<|im_end|>
<|im_start|>user
I was wondering how transformers work?<|im_end|>
<|im_start|>assistant
Quantization
LlamaCPP
Exllama2
FP8
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. Thank you to @kalomaze for providing a model that made this merge possible.
This is one of multiple models to come out in the series by size and model architecture, so look forward to it!
Contact me on Discord for inquiries.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 21.40 |
| IFEval (0-Shot) | 31.66 |
| BBH (3-Shot) | 35.91 |
| MATH Lvl 5 (4-Shot) | 4.38 |
| GPQA (0-shot) | 9.06 |
| MuSR (0-shot) | 19.42 |
| MMLU-PRO (5-shot) | 27.98 |