7-9B Models
Collection
light model merges
•
7 items
•
Updated
•
1
RP model, Niitama 1.1 as a base, nearswapped with one of the smartest 3.1 models "Storm", mostly abliterated.
This is a merge of pre-trained language models.
This model was merged using the NEARSWAP t0.0001 merge algorithm.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: Sao10K/L3.1-8B-Niitama-v1.1+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
layer_range: [0, 32]
- model: akjindal53244/Llama-3.1-Storm-8B
layer_range: [0, 32]
merge_method: nearswap
base_model: Sao10K/L3.1-8B-Niitama-v1.1+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
parameters:
t:
- value: 0.0001
dtype: bfloat16
out_type: float16 #oops
<|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|>
Credit to Alchemonaut.
Credit to woofwolfy for the idea.