Triangle104/Q2.5-R1-7B

Merge

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

Merge Details

Qwen2.5-7B-Instruct tied with Reasoning LORA.

Merge Method

This model was merged using the Passthrough merge method using unsloth/Qwen2.5-7B-Instruct + nbeerbower/R1-Qwen-7B-LORA as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: unsloth/Qwen2.5-7B-Instruct+nbeerbower/R1-Qwen-7B-LORA
dtype: float16
merge_method: passthrough
models:
  - model: unsloth/Qwen2.5-7B-Instruct+nbeerbower/R1-Qwen-7B-LORA
tokenizer_source: unsloth/Qwen2.5-7B

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	3.78
IFEval (0-Shot)	13.46
BBH (3-Shot)	2.55
MATH Lvl 5 (4-Shot)	1.66
GPQA (0-shot)	0.34
MuSR (0-shot)	2.69
MMLU-PRO (5-shot)	2.00