license, tags, model-index

license	tags	model-index
apache-2.0	merge mergekit lazymergekit liminerity/merge3 yam-peleg/Experiment26-7B	name results INEX8-7B task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 73.29 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MSL7/INEX8-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 89.19 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MSL7/INEX8-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 64.47 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MSL7/INEX8-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 77.83 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MSL7/INEX8-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 84.85 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MSL7/INEX8-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 68.99 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MSL7/INEX8-7B Open LLM Leaderboard

MADE WITH LOVE BY LIMINERITY

INEX8-7B

INEX8-7B is a merge of the following models using mergekit:

• liminerity/merge3
• yam-peleg/Experiment26-7B

🧩 Configuration

MODEL_NAME = "merge"
slices:
  - sources:
      - model: MSL7/INEX4-7b
        layer_range: [0, 32]
      - model: yam-peleg/Experiment24-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: MSL7/INEX4-7b
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

MODEL_NAME = "merge1"
slices:
  - sources:
      - model: liminerity/merge
        layer_range: [0, 32]
      - model: CorticalStack/shadow-clown-7B-dare
        layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/merge
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

MODEL_NAME = "merge2"
slices:
  - sources:
      - model: liminerity/merge1
        layer_range: [0, 32]
      - model: bardsai/jaskier-7b-dpo-v6.1
        layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/merge1
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

MODEL_NAME = "merge3"
slices:
  - sources:
      - model: liminerity/merge2
        layer_range: [0, 32]
      - model: eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO
        layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/merge2
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


MODEL_NAME: "INEX8-7b"
slices:
  - sources:
      - model: liminerity/merge3
        layer_range: [0, 32]
      - model: yam-peleg/Experiment26-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/merge3
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.	76.44
AI2 Reasoning Challenge (25-Shot)	73.29
HellaSwag (10-Shot)	89.19
MMLU (5-Shot)	64.47
TruthfulQA (0-shot)	77.83
Winogrande (5-shot)	84.85
GSM8k (5-shot)	68.99