README.md

metadata

base_model:
  - v000000/Llama-3.1-8B-Stheno-v3.4-abliterated
  - akjindal53244/Llama-3.1-Storm-8B
  - Sao10K/Llama-3.1-8B-Stheno-v3.4
library_name: transformers
tags:
  - mergekit
  - merge
  - llama

Llama-3.1-Sthenorm-8B

RP model, Stheno3.4 with one of the smartest 3.1 models, half abliterated.

Thanks mradermacher for the quants:

• GGUF
• GGUF imatrix

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• v000000/Llama-3.1-8B-Stheno-v3.4-abliterated
• akjindal53244/Llama-3.1-Storm-8B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated
        layer_range: [0, 32]
      - model: akjindal53244/Llama-3.1-Storm-8B
        layer_range: [0, 32]
merge_method: slerp
base_model: v000000/Llama-3.1-8B-Stheno-v3.4-abliterated
parameters:
  t:
    - filter: self_attn
      value: [0.1, 0.6, 0.3, 0.8, 0.5]
    - filter: mlp
      value: [0.9, 0.4, 0.7, 0.2, 0.5]
    - value: 0.5
dtype: float32

Prompt Template:

<|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|>