mergekit
merge base_model:
unsloth/Llama-3.2-3B-Instruct
NotASI/FineTome-Llama3.2-3B-1002 model-index:
name: FineTome-v1.5-Llama3.2-3B-1007 results:
- task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics:
  - type: inst_level_strict_acc and prompt_level_strict_acc value: 55.08 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-3B-1007 name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics:
  - type: acc_norm value: 19.46 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-3B-1007 name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics:
  - type: exact_match value: 5.14 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-3B-1007 name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics:
  - type: acc_norm value: 1.57 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-3B-1007 name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics:
  - type: acc_norm value: 4.07 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-3B-1007 name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics:
  - type: acc value: 16.09 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-3B-1007 name: Open LLM Leaderboard

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using unsloth/Llama-3.2-3B-Instruct as a base.

Models Merged

The following models were included in the merge:

NotASI/FineTome-Llama3.2-3B-1002

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: NotASI/FineTome-Llama3.2-3B-1002
    parameters:
      weight: 1
  - model: unsloth/Llama-3.2-3B-Instruct
    parameters:
      weight: 1
merge_method: ties
base_model: unsloth/Llama-3.2-3B-Instruct
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	16.90
IFEval (0-Shot)	55.08
BBH (3-Shot)	19.46
MATH Lvl 5 (4-Shot)	5.14
GPQA (0-shot)	1.57
MuSR (0-shot)	4.07
MMLU-PRO (5-shot)	16.09

RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-8bits

Original model description: