Nexesenex/Llama_3.x_70b_Nemdohertess_v2.0

about

Functional model, despite its low PPL. Good benches. Quite uncensored, especially in chat mode. Instruct mode is working fine.

---

benchs

ARC-C : 63.55 (+++) ARC-E : 83.50 (+++) PPL512 : 3.15 (+++)

---

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 nbeerbower/Llama-3.1-Nemotron-lorablated-70B as a base.

Models Merged

The following models were included in the merge:

• mlabonne/Hermes-3-Llama-3.1-70B-lorablated
• Nexesenex/Llama_3.x_70b_L3.3_Dolphin_128K_v1.02
• migtissera/Tess-3-Llama-3.1-70B

Configuration

The following YAML configuration was used to produce this model:

merge_method: model_stock
models:
  - model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
    parameters:
      weight: 1.0
  - model: Nexesenex/Llama_3.x_70b_L3.3_Dolphin_128K_v1.02
    parameters:
      weight: 1.0
  - model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated
    parameters:
      weight: 1.0
  - model: migtissera/Tess-3-Llama-3.1-70B
    parameters:
      weight: 1.0
base_model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
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