The license is cc-by-nc-4.0
.
GAI-LLM/KoSOLAR-10.7B-mixed-v13
Model Details
Model Developers Donghoon Oh, Hanmin Myung, Eunyoung Kim (SK C&C G.AI Eng)
Input Models input text only.
Output Models generate text only.
Model Architecture
GAI-LLM/KoSOLAR-10.7B-mixed-v13 is an auto-regressive language model based on the LLaMA2 transformer architecture.
Base Model yanolja/KoSOLAR-10.7B-v0.1
Training Dataset
- We combined Open Korean Dateset using mixed-strategy.
- We use A100 GPU 80GB * 8, when training.
Model Benchmark
KO-LLM leaderboard
- Follow up as Open KO-LLM LeaderBoard.
Implementation Code
### GAI-LLM/KoSOLAR-10.7B-mixed-v13
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "GAI-LLM/KoSOLAR-10.7B-mixed-v13"
model = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(repo)
- Downloads last month
- 2,075
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.