merge
mergekit
lazymergekit
liminerity/herbaccbaccules-3b-slerp
KnutJaegersberg/Deita-2b model-index:
name: dhbacmes-3b-slerp results:
- task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics:
  - type: acc_norm value: 45.22 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/dhbacmes-3b-slerp name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics:
  - type: acc_norm value: 70.77 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/dhbacmes-3b-slerp name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics:
  - type: acc value: 52.94 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/dhbacmes-3b-slerp name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics:
  - type: mc2 value: 40.41 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/dhbacmes-3b-slerp name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics:
  - type: acc value: 65.11 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/dhbacmes-3b-slerp name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics:
  - type: acc value: 43.67 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/dhbacmes-3b-slerp name: Open LLM Leaderboard

dhbacmes-3b-slerp

dhbacmes-3b-slerp is a merge of the following models using mergekit:

🧩 Configuration

yaml

slices:
  - sources:
      - model: liminerity/herbaccbaccules-3b-slerp
        layer_range: [0, 40]
      - model: KnutJaegersberg/Deita-2b
        layer_range: [0, 40]
merge_method: slerp
base_model: liminerity/herbaccbaccules-3b-slerp
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

Detailed results can be found here

Metric	Value
Avg.	53.02
AI2 Reasoning Challenge (25-Shot)	45.22
HellaSwag (10-Shot)	70.77
MMLU (5-Shot)	52.94
TruthfulQA (0-shot)	40.41
Winogrande (5-shot)	65.11
GSM8k (5-shot)	43.67

RichardErkhov/liminerity_-_dhbacmes-3b-slerp-4bits

Original model description:

dhbacmes-3b-slerp

🧩 Configuration

Open LLM Leaderboard Evaluation Results

RichardErkhov/
liminerity_-_dhbacmes-3b-slerp-4bits