merge

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

Merge Details

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:

models:
  - model: Nitral-AI/Echidna-7b-128k
    parameters:
      weight: 3.0
  - model: Jebadiah/Llama-3-8B-source-lewd-context-function-calling
    parameters:
      weight: 0.3
merge_method: linear
dtype: float16

Downloads last month: 2

Safetensors

Model size

7B params

Tensor type

F16

Model tree for Jebadiah/Aria-7b-128k-v2

Jebadiah/Llama-3-8B-source-lewd-context-function-calling

Nitral-Archive/Echidna-7b-128k

Merge model

this model

Merges

1 model

Quantizations

1 model

Paper for Jebadiah/Aria-7b-128k-v2

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Paper • 2203.05482 • Published Mar 10, 2022 • 7