G2-MS-Nyxora-27b
Now that the cute anime girl has your attention.
Creator: SteelSkull
About G2-MS-Nyxora-27b:
Model Name Legend =
"G2 = Gemma 2"
"MS = Model_stock"This model represents an experimental foray into 27b models. Feedback is welcome for further improvements.
G2-MS-Nyxora-27b combines multiple models' strengths to provide a versatile assistant for various tasks, including general use, storytelling, and roleplay (ERP & RP).
The Model seems to be on the prudish side from google's training but seems to be fixed with a good system prompt. (Provided in files)
The Model_stock merge method ensures the model remains focused, tailored, and high-quality.
Quants:
Will add as found or im notified of their creation (If you know of one create a discussion!)
Config:
MODEL_NAME = "G2-MS-Nyxora-27b"
yaml_config = """
base_model: google/gemma-2-27b-it
merge_method: model_stock
dtype: bfloat16
models:
- model: TheDrummer/Big-Tiger-Gemma-27B-v1
- model: migtissera/Tess-v2.5-Gemma-2-27B-alpha
"""Template:
<start_of_turn>user
{{ if .System }}{{ .System }} {{ end }}{{ .Prompt }}<end_of_turn>
<start_of_turn>model
{{ .Response }}<end_of_turn>Source Model Details:
TheDrummer/Big-Tiger-Gemma-27B-v1:
A decensored version of the Gemma 27B model.
migtissera/Tess-v2.5-Gemma-2-27B-alpha:
The latest state-of-the-art model in the Tess series, Tess-v2.5.2, offers significant improvements in reasoning, coding, and mathematics. It ranks #1 on the MMLU benchmark among open weight models and outperforms several frontier closed models.
Gemma-2-27b-it:
A lightweight, state-of-the-art model from Google, well-suited for various text generation tasks. Its small size allows deployment in resource-limited environments, fostering AI innovation for all.
Merge Method Details:
Model_stock Uses some neat geometric properties of fine tuned models to compute good weights for linear interpolation.
I've had a few people ask about donations so here's a link:
- Downloads last month
- 25