Downloads · 30 days
12
0% of all-time downloads
llama-2-koen-13b-mixed-v7
GAI-LLM/llama-2-koen-13b-mixed-v7
llama-2-koen-13b-mixed-v7 is a text generation model from GAI-LLM. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
All-time downloads
46.6K
Public
Repo size
52.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin26.3 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- llama
- Access
- Public
- Created
- Nov 3, 2023
- Updated
- Nov 3, 2023
- SHA
- 3acbc91f
Model card
From the Hugging Face model README
The license is cc-by-nc-4.0.
GAI-LLM/llama-2-koen-13b-mixed-v7
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/llama-2-koen-13b-mixed-v7 is an auto-regressive language model based on the LLaMA2 transformer architecture.
Base Model beomi/llama-2-koen-13b
Training Dataset
-
We combined Open Korean Dateset using mixed-strategy.
- Kopen-platypus + Koalpaca_v1.1 + kaist_cot_deepL + dolly_qa_task
-
We use A100 GPU 80GB * 8, when training.
Model Benchmark
KO-LLM leaderboard
- Follow up as Open KO-LLM LeaderBoard.
Implementation Code
### GAI-LLM/llama-2-koen-13b-mixed-v7
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "GAI-LLM/llama-2-koen-13b-mixed-v7"
model = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(repo)
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- cc-by-nc-4.0
- Languages
- ko
- Created
- Nov 3, 2023
- Updated
- Nov 3, 2023