Sorawiz/Qwen2.5-7B-Test

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 jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.8 as a base.

Models Merged

The following models were included in the merge:

• Sorawiz/Marco-o1-Base
• EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1 + ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
• HumanLLMs/Human-Like-Qwen2.5-7B-Instruct + ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
• allura-org/Teleut-7b-RP + ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Sorawiz/Marco-o1-Base
  - model: HumanLLMs/Human-Like-Qwen2.5-7B-Instruct+ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
  - model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1+ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
  - model: allura-org/Teleut-7b-RP+ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
merge_method: model_stock
base_model: jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.8
parameters:
  filter_wise: false
dytpe: float32