PracticeLLM/Custom-KoLLM-13B-v5

⭐My custom LLM 13B⭐

Model Details

Model Developers

• Kyujin Han (kyujinpy)

Model Architecture

• My custom LLM 13B is an auto-regressive language model based on the LLaMA2 transformer architecture.

Base Model

• beomi/llama-2-koen-13b

Training Dataset

• kyujinpy/KOR-gugugu-platypus-set.

---

Model comparisons

Ko-LLM leaderboard(11/27; link)

Model	Average	Ko-ARC	Ko-HellaSwag	Ko-MMLU	Ko-TruthfulQA	Ko-CommonGen V2
⭐My custom LLM 13B-v1⭐	50.19	45.99	56.93	41.78	41.66	64.58
⭐My custom LLM 13B-v4⭐	49.89	45.05	57.06	41.83	42.93	62.57
⭐My custom LLM 13B-v5⭐	49.50	44.88	56.74	42.23	42.82	60.80

---

Model comparisons2

AI-Harness evaluation; link

Model	Copa	Copa	HellaSwag	HellaSwag	BoolQ	BoolQ	Sentineg	Sentineg
	0-shot	5-shot	0-shot	5-shot	0-shot	5-shot	0-shot	5-shot
⭐My custom LLM 13B-v1⭐	0.7987	0.8269	0.4994	0.5660	0.3343	0.5060	0.6984	0.9723
⭐My custom LLM 13B-v4⭐**	0.7988	0.8279	0.4995	0.4953	0.3343	0.3558	0.7825	0.9698
⭐My custom LLM 13B-v5⭐	0.8028	0.8329	0.5082	0.5136	0.8647	0.8500	0.5524	0.9723
beomi/llama-2-koen-13b	0.7768	0.8128	0.4999	0.5127	0.3988	0.7038	0.5870	0.9748

---

Implementation Code

### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "PracticeLLM/Custom-KoLLM-13B-v5"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)