Triangle104/Mistral-Small-24b-Harmony

Merge

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

Merge Details

Merging Mistral-Small-24B Base and Instruct models together to try and create... Harmony?

Quant: https://huggingface.co/Triangle104/Mistral-Small-24b-Harmony-Q4_K_S-GGUF

Merge Method

This model was merged using the TIES merge method using mistralai/Mistral-Small-24B-Instruct-2501 as a base.

Models Merged

The following models were included in the merge:

• mistralai/Mistral-Small-24B-Base-2501

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mistralai/Mistral-Small-24B-Base-2501
    parameters:
      density: 1
      weight: 1
  - model: mistralai/Mistral-Small-24B-Instruct-2501
    parameters:
      density: 1
      weight: 1

merge_method: ties
base_model: mistralai/Mistral-Small-24B-Instruct-2501
parameters:
  normalize: false
  int8_mask: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	27.17
IFEval (0-Shot)	16.87
BBH (3-Shot)	48.42
MATH Lvl 5 (4-Shot)	19.11
GPQA (0-shot)	17.90
MuSR (0-shot)	11.48
MMLU-PRO (5-shot)	49.23