Cerberus-7B-slerp

Cerberus-7B-slerp is a merge of the following models using mergekit:

• fblgit/UNA-TheBeagle-7b-v1
• UCLA-AGI/zephyr-7b-sft-full-SPIN-iter3

🧩 Configuration

slices:
  - sources:
      - model: fblgit/UNA-TheBeagle-7b-v1
        layer_range: [0, 32]
      - model: UCLA-AGI/zephyr-7b-sft-full-SPIN-iter3
        layer_range: [0, 32]
merge_method: slerp
base_model: fblgit/UNA-TheBeagle-7b-v1
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	63.46
AI2 Reasoning Challenge (25-Shot)	69.54
HellaSwag (10-Shot)	87.33
MMLU (5-Shot)	63.25
TruthfulQA (0-shot)	61.35
Winogrande (5-shot)	81.29
GSM8k (5-shot)	17.97