merge

Name: Llama_3.2_1b_Odyssea_V1
Availability: InStock

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using meditsolutions/Llama-3.2-SUN-1B-chat as a base.

Models Merged

The following models were included in the merge:

Nexesenex/Llama_3.2_1b_Synopsys_0.1
Nexesenex/Llama_3.2_1b_AquaSyn_0.1

Configuration

The following YAML configuration was used to produce this model:

yaml

merge_method: model_stock
models:
  - model: Nexesenex/Llama_3.2_1b_AquaSyn_0.1
    parameters:
      weight: 1.0
  - model: Nexesenex/Llama_3.2_1b_Synopsys_0.1
    parameters:
      weight: 1.0
base_model: meditsolutions/Llama-3.2-SUN-1B-chat
dtype: bfloat16
normalize: true

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	5.72
IFEval (0-Shot)	25.53
BBH (3-Shot)	2.65
MATH Lvl 5 (4-Shot)	1.44
GPQA (0-shot)	1.12
MuSR (0-shot)	1.92
MMLU-PRO (5-shot)	1.70

Nexesenex/Llama_3.2_1b_Odyssea_V1