README.md

metadata

base_model:
  - sethuiyer/Medichat-Llama3-8B
  - mlabonne/ChimeraLlama-3-8B-v3
  - johnsnowlabs/JSL-MedLlama-3-8B-v2.0
library_name: transformers
tags:
  - mergekit
  - merge
license: llama3

medLlama-3-8B_DARE

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using mlabonne/ChimeraLlama-3-8B-v3 as a base.

Models Merged

The following models were included in the merge:

• sethuiyer/Medichat-Llama3-8B
• johnsnowlabs/JSL-MedLlama-3-8B-v2.0

Evaluation

• multimedq (0 shot)
  

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
- medmcqa	Yaml	none	0	acc	0.5728	±	0.0076
		none	0	acc_norm	0.5728	±	0.0076
- medqa_4options	Yaml	none	0	acc	0.5923	±	0.0138
		none	0	acc_norm	0.5923	±	0.0138
- anatomy (mmlu)	0	none	0	acc	0.7111	±	0.0392
- clinical_knowledge (mmlu)	0	none	0	acc	0.7547	±	0.0265
- college_biology (mmlu)	0	none	0	acc	0.7917	±	0.0340
- college_medicine (mmlu)	0	none	0	acc	0.6647	±	0.0360
- medical_genetics (mmlu)	0	none	0	acc	0.8200	±	0.0386
- professional_medicine (mmlu)	0	none	0	acc	0.7426	±	0.0266
stem	N/A	none	0	acc_norm	0.5773	±	0.0067
		none	0	acc	0.6145	±	0.0057
- pubmedqa	1	none	0	acc	0.7400	±	0.0196

Groups	Version	Filter	n-shot	Metric	Value		Stderr
stem	N/A	none	0	acc_norm	0.5773	±	0.0067
		none	0	acc	0.6145	±	0.0057

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mlabonne/ChimeraLlama-3-8B-v3
    # No parameters necessary for base model

  - model: sethuiyer/Medichat-Llama3-8B
    parameters:
      density: 0.53
      weight: 0.5
  - model: johnsnowlabs/JSL-MedLlama-3-8B-v2.0
    parameters:
      density: 0.53
      weight: 0.5
      
merge_method: dare_ties
base_model: mlabonne/ChimeraLlama-3-8B-v3
parameters:
  int8_mask: true
dtype: float16