README.md

metadata

base_model:
  - schonsense/Llama-3.3-70B-Inst-Ablit-Flammades-SLERP
  - Blackroot/Mirai-3.0-70B
  - Sao10K/L3.3-70B-Euryale-v2.3
  - flammenai/Llama3.1-Flammades-70B
  - TsinghuaC3I/Llama-3-70B-UltraMedical
library_name: transformers
tags:
  - mergekit
  - merge

Flamlama_della_70B

This model produces unique prose, but is virtually unuseable without babysitting each generation. It was created explicitly to add flavor and ability to a base model.

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

Merge Details

Merge Method

This model was merged using the della merge method using schonsense\Llama-3.3-70B-Inst-Ablit-Flammades-SLERP as a base.

Models Merged

The following models were included in the merge:

• Blackroot\Mirai-3.0-70B
• flammenai\Llama3.1-Flammades-70B
• TsinghuaC3I\Llama-3-70B-UltraMedical
• Sao10K\L3.3-70B-Euryale-v2.3

Configuration

The following YAML configuration was used to produce this model:

name: Flam_della_70B
models:
  - model: schonsense\Llama-3.3-70B-Inst-Ablit-Flammades-SLERP
  - model: Blackroot\Mirai-3.0-70B
    parameters:
      density: .8
      weight: .8
  - model: Sao10K\L3.3-70B-Euryale-v2.3
    parameters:
      density: .8
      weight: .8
  - model: flammenai\Llama3.1-Flammades-70B
    parameters:
      density: .8
      weight: .8
  - model: TsinghuaC3I\Llama-3-70B-UltraMedical
    parameters:
      density: .8
      weight: .8
merge_method: della
base_model: schonsense\Llama-3.3-70B-Inst-Ablit-Flammades-SLERP
tokenizer_source: schonsense\Llama-3.3-70B-Inst-Ablit-Flammades-SLERP
parameters:
  normalize: true
  int8_mask: true
  lambda: 1.0
  epsilon: 0.1
dtype: float16