about

Original name : Llama_3.x_70b_Dolnemhertulimtess_v1.0

Also known as : Llama_3.x_70b_Dolmen_v1.0 (1.1 will come soon)

This model is essentially a Llama 3.1 smart brick based on by a 3.0->3.3 "port", to be used in second level merges.

This time, for the base, I used a Llama 3.0 Dolphin 2.9.1/Llama 3.3 instruct abliterated merge, in order to get both the capabilities of each model, and notably Dolphin, not ported on Llama 70b 3.1 or 3.3 by CognitiveComputations.

Then, I added the best 'instructions oriented' finetunes I know, simple as that.

The model is highly uncensored, quite intelligent, and can be used as a standalone.

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Nexesenex/Llama_3.x_70b_L3.3_Dolphin_128K_v1.02 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: model_stock
models:
  - model: Nexesenex/Llama_3.x_70b_L3.3_Dolphin_128K_v1.02
    parameters:
      weight: 1.0
  - model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
    parameters:
      weight: 1.0
  - model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated
    parameters:
      weight: 1.0
  - model: huihui-ai/Llama-3.1-Tulu-3-70B-abliterated
    parameters:
      weight: 1.0
  - model: huihui-ai/Tess-R1-Limerick-Llama-3.1-70B-abliterated
    parameters:
      weight: 1.0
  - model: migtissera/Tess-3-Llama-3.1-70B
    parameters:
      weight: 1.0
base_model: Nexesenex/Llama_3.x_70b_L3.3_Dolphin_128K_v1.02
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: false
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union