iRASC_-_BioLlama-Ko-8B-gguf

RichardErkhov/iRASC_-_BioLlama-Ko-8B-gguf

iRASC_-_BioLlama-Ko-8B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

Downloads · 30 days

0% of all-time downloads

All-time downloads

Public

Repo size

92.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf108 GB · 100%

At a glance

Access: Public
Created: Aug 21, 2024
Updated: Aug 21, 2024
SHA: 348b9403

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

BioLlama-Ko-8B - GGUF

Model creator: https://huggingface.co/iRASC/
Original model: https://huggingface.co/iRASC/BioLlama-Ko-8B/

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

Original model description:

base_model:

beomi/Llama-3-Open-Ko-8B
ProbeMedicalYonseiMAILab/medllama3-v20 library_name: transformers tags:
mergekit
merge license: apache-2.0 datasets:
sean0042/KorMedMCQA

BioLlama-Ko-8B

image/png

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

🏆 Evaluation

kormedmcqa(한국어 의학 벤치마크)

Model	Doctor	Nurse	Pharm	Avg
gpt-4-0613	75.09	85.86	83.22	81.39
iRASC/BioLlama-Ko-8B	45.26	63.37	58.47	55.70
gpt-3.5-turbo-0613	41.75	62.18	56.35	53.43
llama2-70b	42.46	63.54	53.26	53.09
SOLAR-10.7B-v1.0	37.19	55.54	54.07	48.93
ProbeMedicalYonseiMAILab/medllama3-v20	37.19	54.68	50.65	47.51
beomi/Llama-3-Open-Ko-8B	38.95	53.49	46.09	46.18

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using ProbeMedicalYonseiMAILab/medllama3-v20 as a base.

Models Merged

The following models were included in the merge:

beomi/Llama-3-Open-Ko-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ProbeMedicalYonseiMAILab/medllama3-v20
  - model: beomi/Llama-3-Open-Ko-8B
    parameters:
      density: 0.8
      weight: 0.45
merge_method: dare_ties
base_model: ProbeMedicalYonseiMAILab/medllama3-v20
parameters:
  int8_mask: true
dtype: bfloat16

Created: Aug 21, 2024
Updated: Aug 21, 2024