Experimental Model Merge ⚗️
Collection
Experimental Model Merge using mergekit FP16 Weight
•
7 items
•
Updated
•
2
This is a merge of pre-trained language models created using mergekit.
I'm trying to combine the best model from Sao10k. And turn out, this is beyond my expectation. I use it for RP and ERP on scenario card. And it follow the instruction very well (At least for me). All credits and thanks go to Sao10k for providing amazing models used in the merge.
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{output}<|eot_id|>
Temprature: 1.3
Min-P: 0.1
// If using DRY
Multiplier: 2
Base: 1.75
Allowed Length: 2
Penalty Range: 0
This model was merged using the della merge method using Sao10K/L3-8B-Niitama-v1 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model: Sao10K/L3-8B-Niitama-v1
merge_method: della
dtype: bfloat16
models:
- model: Sao10K/L3-8B-Lunaris-v1
parameters:
weight: 1.0
- model: Sao10K/L3-8B-Stheno-v3.2
parameters:
weight: 1.0
- model: Sao10K/L3-8B-Niitama-v1
parameters:
weight: 1.0
- model: Sao10K/L3-8B-Tamamo-v1
parameters:
weight: 1.0