KaraKaraWitch/BlenderCartel-MS-llama33-70B

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

Model Vibes

• Seems to be cogito / base-model coded but a perchace of BlenderCartel Part 1 and Part 2 things.
• Can have refusals, probably not good in my book really.

Chat Format

Use Llama-3 for instruct, don't use ChatML since that introduces refusals way more.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using deepcogito/cogito-v2-preview-llama-70B as a base.

Models Merged

The following models were included in the merge:

• KaraKaraWitch/BlenderCartel-llama33-70B-Pt2
• KaraKaraWitch/BlenderCartel-llama33-70B-Pt1

Configuration

The following YAML configuration was used to produce this model:

models:
  # Part 1
  - model: KaraKaraWitch/BlenderCartel-llama33-70B-Pt1
  # Part 2
  - model: KaraKaraWitch/BlenderCartel-llama33-70B-Pt2

merge_method: model_stock
base_model: deepcogito/cogito-v2-preview-llama-70B
parameters:
  normalize: true
dtype: bfloat16