Jason1903_SLERP

Jason1903_SLERP is a merge of the following models using mergekit:

• yam-peleg/Experiment26-7B
• chihoonlee10/T3Q-Mistral-Orca-Math-DPO

🧩 Configuration

slices:
  - sources:
      - model: yam-peleg/Experiment26-7B
        layer_range: [0, 32]
      - model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
        layer_range: [0, 32]
merge_method: slerp
base_model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
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: float16

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |76.77|
|AI2 Reasoning Challenge (25-Shot)|73.12|
|HellaSwag (10-Shot)              |89.13|
|MMLU (5-Shot)                    |64.43|
|TruthfulQA (0-shot)              |78.13|
|Winogrande (5-shot)              |85.08|
|GSM8k (5-shot)                   |70.74|