merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using Qwen/Qwen2.5-7B-Instruct as a base.

Models Merged

The following models were included in the merge:

• EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
• HumanLLMs/Human-Like-Qwen2.5-7B-Instruct
• Qwen/Qwen2.5-7B-Instruct-1M
• Qwen/Qwen2.5-Math-7B
• deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
• Qwen/Qwen2.5-Coder-7B
• fblgit/cybertron-v4-qw7B-UNAMGS
• prithivMLmods/QwQ-LCoT2-7B-Instruct
• huihui-ai/Qwen2.5-7B-Instruct-abliterated
• Rombo-Org/Rombo-LLM-V2.5-Qwen-7b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen2.5-Math-7B
    parameters:
      weight: 1
  - model: Qwen/Qwen2.5-Coder-7B
    parameters:
      weight: 1
  - model: Qwen/Qwen2.5-7B-Instruct-1M
    parameters:
      weight: 1
  - model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
    parameters:
      weight: 1
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
    parameters:
      weight: 1
  - model: HumanLLMs/Human-Like-Qwen2.5-7B-Instruct
    parameters:
      weight: 1
  - model: fblgit/cybertron-v4-qw7B-UNAMGS
    parameters:
      weight: 1
  - model: Rombo-Org/Rombo-LLM-V2.5-Qwen-7b
    parameters:
      weight: 1
  - model: huihui-ai/Qwen2.5-7B-Instruct-abliterated
    parameters:
      weight: 1
  - model: prithivMLmods/QwQ-LCoT2-7B-Instruct
    parameters:
      weight: 1
merge_method: ties
base_model: Qwen/Qwen2.5-7B-Instruct
parameters:
  normalize: true
  int8_mask: true
tokenizer_source: Qwen/Qwen2.5-7B-Instruct
dtype: bfloat16