LLama3-Lexi-Aura-3Some-SLERP-SLERP 8B and 15B!
Collection
Slerped Aura and 3some, then slerped that outcome with Lexi uncensored. Its very compliant and uncensored. Quantized 8b by Mradermacher, big thanks :)
•
5 items
•
Updated
•
1
This is a merge of pre-trained language models created using mergekit.
I dont know if its still as uncensored as the original, but it has function calling, which is, cool i guess.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP
layer_range:
- 0
- 32
- model: mzbac/llama-3-8B-Instruct-function-calling-v0.2
layer_range:
- 0
- 32
merge_method: slerp
base_model: Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP
parameters:
t:
- filter: self_attn
value:
- 0
- 0.5
- 0.3
- 0.7
- 1
- filter: mlp
value:
- 1
- 0.5
- 0.7
- 0.3
- 0
- value: 0.5
dtype: bfloat16