You can deploy this model and start earning money today!

RichardErkhov/
ChenWeiLi_-_MedLlama-3-8B_DARE-gguf

Name: ChenWeiLi_-_MedLlama-3-8B_DARE-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MedLlama-3-8B_DARE - GGUF

Model creator: https://huggingface.co/ChenWeiLi/
Original model: https://huggingface.co/ChenWeiLi/MedLlama-3-8B_DARE/

Name	Quant method	Size
MedLlama-3-8B_DARE.Q2_K.gguf	Q2_K	2.96GB
MedLlama-3-8B_DARE.IQ3_XS.gguf	IQ3_XS	3.28GB
MedLlama-3-8B_DARE.IQ3_S.gguf	IQ3_S	3.43GB
MedLlama-3-8B_DARE.Q3_K_S.gguf	Q3_K_S	3.41GB
MedLlama-3-8B_DARE.IQ3_M.gguf	IQ3_M	3.52GB
MedLlama-3-8B_DARE.Q3_K.gguf	Q3_K	3.74GB
MedLlama-3-8B_DARE.Q3_K_M.gguf	Q3_K_M	3.74GB
MedLlama-3-8B_DARE.Q3_K_L.gguf	Q3_K_L	4.03GB
MedLlama-3-8B_DARE.IQ4_XS.gguf	IQ4_XS	4.18GB
MedLlama-3-8B_DARE.Q4_0.gguf	Q4_0	4.34GB
MedLlama-3-8B_DARE.IQ4_NL.gguf	IQ4_NL	4.38GB
MedLlama-3-8B_DARE.Q4_K_S.gguf	Q4_K_S	4.37GB
MedLlama-3-8B_DARE.Q4_K.gguf	Q4_K	4.58GB
MedLlama-3-8B_DARE.Q4_K_M.gguf	Q4_K_M	4.58GB
MedLlama-3-8B_DARE.Q4_1.gguf	Q4_1	4.78GB
MedLlama-3-8B_DARE.Q5_0.gguf	Q5_0	5.21GB
MedLlama-3-8B_DARE.Q5_K_S.gguf	Q5_K_S	5.21GB
MedLlama-3-8B_DARE.Q5_K.gguf	Q5_K	5.34GB
MedLlama-3-8B_DARE.Q5_K_M.gguf	Q5_K_M	5.34GB
MedLlama-3-8B_DARE.Q5_1.gguf	Q5_1	5.65GB
MedLlama-3-8B_DARE.Q6_K.gguf	Q6_K	6.14GB
MedLlama-3-8B_DARE.Q8_0.gguf	Q8_0	7.95GB

Original model description:

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:

Evaluation

multimedq (0 shot)

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

yaml

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

RichardErkhov/ChenWeiLi_-_MedLlama-3-8B_DARE-gguf