bunnycore/Qwen2.5-3B-Model-Stock-v3.2

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/Qwen2.5-3B-Instruct as a base.

Models Merged

The following models were included in the merge:

• bunnycore/QwQen-3B-LCoT + bunnycore/Qwen-2.5-3b-R1-lora_model-v.1
• bunnycore/Qwen2.5-3B-RP-Thinker-V2 + bunnycore/Qwen-2.5-s1k-R1-lora-v1.1
• bunnycore/Qwen2.5-3B-Model-Stock-v2

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bunnycore/Qwen2.5-3B-RP-Thinker-V2+bunnycore/Qwen-2.5-s1k-R1-lora-v1.1
  - model: bunnycore/Qwen2.5-3B-Model-Stock-v2
  - model: bunnycore/QwQen-3B-LCoT+bunnycore/Qwen-2.5-3b-R1-lora_model-v.1
base_model: Qwen/Qwen2.5-3B-Instruct
merge_method: model_stock
parameters:
  normalize: true
dtype: bfloat16
tokenizer_source: Qwen/Qwen2.5-3B-Instruct

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	27.39
IFEval (0-Shot)	63.53
BBH (3-Shot)	26.33
MATH Lvl 5 (4-Shot)	37.54
GPQA (0-shot)	4.47
MuSR (0-shot)	6.97
MMLU-PRO (5-shot)	25.49