metadata
tags:
- roleplay
- creative-writing
- merge
- mergekit
base_model:
- Delta-Vector/Hamanasu-Magnum-QwQ-32B
- Sao10K/32B-Qwen2.5-Kunou-v1
pipeline_tag: text-generation
library_name: transformers
__~a~_
~~; ~_
_ ~ ~_ _
'_\;__._._._._._._] ~_._._._._._.__;/_`
'(/'/'/'/'|'|'|'| ( )|'|'|'|'\'\'\'\)'
(/ / / /, | | | |(/ \) | | | ,\ \ \ \)
(/ / / / / | | | ~(/ \) ~ | | \ \ \ \ \)
(/ / / / / ~ ~ ~ (/ \) ~ ~ \ \ \ \ \)
(/ / / / ~ / (||)| ~ \ \ \ \)
~ / / ~ M /||\M ~ \ \ ~
~ ~ /||\ ~ ~
//||\\
//||\\
//||\\
'/||\' "Archaeopteryx"
THESE ARE EXL2 QUANTS, LOOK IN THE REVISIONS FOR THE QUANTS, MAIN BRANCH CONTAINS MEASUREMENT.
A series of Merges made for Roleplaying & Creative Writing, This model uses 32B-Qwen2.5-Kunou-v1 and Hamanasu-Magnum-QwQ-32B and Slerp to merge the 2 models.
ChatML formatting
"""<|im_start|>system
system prompt<|im_end|>
<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""
MergeKit Configuration
models:
- model: Sao10K/32B-Qwen2.5-Kunou-v1
- model: Delta-Vector/Hamanasu-Magnum-QwQ-32B
merge_method: slerp
base_model: Delta-Vector/Hamanasu-Magnum-QwQ-32B
parameters:
t:
- value: 0.2
dtype: bfloat16
tokenizer_source: base
Quants:
Credits
Thank you to: Kubernetes-bad, LucyKnada, Intervitens, Samantha Twinkman, Tav, Trappu & The rest of Anthracite