Resolving Interference When Merging Models
Paper
• 2306.01708 • Published
• 17
This is quantized version of Triangle104/Chatty-Harry_V3.0 created using llama.cpp
You've got to ask yourself one question...
Added some Chronos-Gold-12B-1.0 at suggestion.
Feedback is welcome.
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using Triangle104/ChatWaifu_Magnum_V0.2 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: elinas/Chronos-Gold-12B-1.0
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: Triangle104/ChatWaifu_Magnum_V0.2
parameters:
normalize: false
int8_mask: true
dtype: float16
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit