Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge

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

Built with Meta Llama 3.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: princeton-nlp/Llama-3-Instruct-8B-SimPO
    layer_range:
    - 0
    - 32
  - model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
    layer_range:
    - 0
    - 32
merge_method: slerp
base_model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
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. 20.74
IFEval (0-Shot) 42.71
BBH (3-Shot) 28.26
MATH Lvl 5 (4-Shot) 9.37
GPQA (0-shot) 5.37
MuSR (0-shot) 9.54
MMLU-PRO (5-shot) 29.17
Downloads last month
4,889
Safetensors
Model size
8.03B params
Tensor type
BF16
Β·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge

Spaces using grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge 7

Collection including grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge

Evaluation results