TareksLab/Sapphire-V2-LLaMa-70B

MERGE2

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 huihui-ai/Llama-3.3-70B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

• MaziyarPanahi/calme-2.3-llama3.1-70b
• pankajmathur/orca_mini_v8_1_70b
• NousResearch/Hermes-3-Llama-3.1-70B
• VAGOsolutions/Llama-3.1-SauerkrautLM-70b-Instruct
• allenai/Llama-3.1-Tulu-3-70B
• OpenBuddy/openbuddy-llama3.3-70b-v24.1-131k
• nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: NousResearch/Hermes-3-Llama-3.1-70B
  - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
  - model: allenai/Llama-3.1-Tulu-3-70B
  - model: pankajmathur/orca_mini_v8_1_70b
  - model: MaziyarPanahi/calme-2.3-llama3.1-70b
  - model: VAGOsolutions/Llama-3.1-SauerkrautLM-70b-Instruct
  - model: OpenBuddy/openbuddy-llama3.3-70b-v24.1-131k
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
merge_method: model_stock
parameters:
  int8_mask: true
dtype: float32
out_dtype: bfloat16
chat_template: llama3
tokenizer:
 source: union
 pad_to_multiple_of: 8