about

A DL-worthy model, merge of Nemotron Abliterated and Llama 3.3 Instruct, with L3.1 Instruct 70b as a base. And it's quite smart and verbose, albeit quite a bit prudish. One of my favorites ATM.

Note : if someone could reproduce the recipe with huihui's Llama 3.3 70b Instruct abliterated (normal version, not the "finetuned") instead of Llama 3.3 70b Instruct, it'd be worth a try.

I don't have access to a mergekit rig atm, now that Arcee's space is down.

merge

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

Merge Details

Merge Method

This model was merged using the Task Arithmetic merge method using meta-llama/Llama-3.1-70B-Instruct 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: task_arithmetic
base_model: meta-llama/Llama-3.1-70B-Instruct
models:
  - model: huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
    parameters:
      weight: 1.0
  - model: meta-llama/Llama-3.3-70B-Instruct
    parameters:
      weight: 1.0
dtype: bfloat16 -> replace with float32 if possible
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: false
  rescale: false
  filter_wise: false
chat_template: auto
tokenizer:
  source: union