7-9B Models
Collection
light model merges
•
7 items
•
Updated
•
1
Why choose?
The full model name is "Llama-3-8B-Poppy-Sunspice"
RP Model, pretty creative.
This has a tendency for endless generations. It likes a bit of penalty parameters if this occurs.
This is a merge of pre-trained language models created using mergekit.
This model was merged using the linear merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: crestf411/L3-8B-sunfall-abliterated-v0.1
parameters:
weight: 0.1
- model: Nitral-AI/Poppy_Porpoise-0.72-L3-8B
parameters:
weight: 0.3
- model: Nitral-Archive/Poppy_Porpoise-Biomix
parameters:
weight: 0.1
- model: Sao10K/L3-8B-Stheno-v3.1
parameters:
weight: 0.2
- model: Hastagaras/HALU-8B-LLAMA3-BRSLURP
parameters:
weight: 0.1
- model: cgato/L3-TheSpice-8b-v0.8.3
parameters:
weight: 0.2
merge_method: linear
dtype: float16
<|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|>