djuna/Q2.5-Fuppavy-7B

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 Qwen/Qwen2.5-7B as a base.

Models Merged

The following models were included in the merge:

• Kortix/FastApply-7B-v1.0
• Qwen/Qwen2.5-Math-7B-Instruct
• huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
• EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
• rombodawg/Rombos-LLM-V2.5-Qwen-7b
• MadeAgents/Hammer2.0-7b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen2.5-7B
  - model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
  - model: huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
  - model: rombodawg/Rombos-LLM-V2.5-Qwen-7b
  - model: Kortix/FastApply-7B-v1.0
  - model: MadeAgents/Hammer2.0-7b
  - model: Qwen/Qwen2.5-Math-7B-Instruct
merge_method: model_stock
base_model: Qwen/Qwen2.5-7B
tokenizer_source: Kortix/FastApply-7B-v1.0
dtype: float32
out_dtype: bfloat16