bunnycore/FuseQwQen-7B

merge

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• FuseAI/FuseChat-Qwen-2.5-7B-Instruct
• fblgit/cybertron-v4-qw7B-UNAMGS + bunnycore/Qwen-2.1-7b-Persona-lora_model
• prithivMLmods/QwQ-LCoT-7B-Instruct
• fblgit/cybertron-v4-qw7B-UNAMGS

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: FuseAI/FuseChat-Qwen-2.5-7B-Instruct
    parameters:
      weight: 0.5
  - model: prithivMLmods/QwQ-LCoT-7B-Instruct
    parameters:
      weight: 1.0
  - model: fblgit/cybertron-v4-qw7B-UNAMGS
    parameters:
      weight: 0.3
  - model: fblgit/cybertron-v4-qw7B-UNAMGS+bunnycore/Qwen-2.1-7b-Persona-lora_model
    parameters:
      weight: 0.6
merge_method: linear
normalize: false
int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	29.40
IFEval (0-Shot)	72.75
BBH (3-Shot)	35.91
MATH Lvl 5 (4-Shot)	12.01
GPQA (0-shot)	5.93
MuSR (0-shot)	11.98
MMLU-PRO (5-shot)	37.85

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	34.68
IFEval (0-Shot)	72.75
BBH (3-Shot)	35.91
MATH Lvl 5 (4-Shot)	43.66
GPQA (0-shot)	5.93
MuSR (0-shot)	11.98
MMLU-PRO (5-shot)	37.85