bunnycore/Qwen2.5-7B-Instruct-Merge-Stock-v0.1

Thinking Mode:

Think about the reasoning process in the mind first, then provide the answer.
The reasoning process should be wrapped within <think> </think> tags, then provide the answer after that, i.e., <think> reasoning process here </think> answer.

Merge Method

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

Models Merged

The following models were included in the merge:

• bunnycore/Qwen-2.5-7B-R1-Stock
• Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
• suayptalha/Clarus-7B-v0.3 + bunnycore/Qwen-2.5-7b-s1k-lora_model
• Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview + bunnycore/Qwen-2.5-7b-s1k-lora_model
• bunnycore/QandoraExp-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview+bunnycore/Qwen-2.5-7b-s1k-lora_model
    parameters:
      weight: 0.5
  - model: bunnycore/QandoraExp-7B
  - model: bunnycore/Qwen-2.5-7B-R1-Stock
  - model: Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
  - model: suayptalha/Clarus-7B-v0.3+bunnycore/Qwen-2.5-7b-s1k-lora_model
base_model: Qwen/Qwen2.5-7B-Instruct
merge_method: model_stock
parameters:
dtype: bfloat16
tokenizer_source: Qwen/Qwen2.5-7B-Instruct

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	36.14
IFEval (0-Shot)	75.09
BBH (3-Shot)	36.40
MATH Lvl 5 (4-Shot)	48.94
GPQA (0-shot)	7.16
MuSR (0-shot)	11.69
MMLU-PRO (5-shot)	37.59