eidolrestore

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merged mostly to test restoring the vocabulary to its padded size. -wyrd is an intervention on -abliterated somewhat related to creativity direction.

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: linear
models:
  - model: Lambent/Eidolon-v3-14B-wyrd
  - model: Lambent/Eidolon-v3-14B-abliterated
parameters:
  weight: 0.5
tokenizer:
  source: union
  pad_to_multiple_of: 512
Downloads last month
18
Safetensors
Model size
14.8B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Lambent/Eidolon-v3.1-14B

Finetuned
(1)
this model
Quantizations
2 models