metadata

language:
  - en
  - ko
datasets:
  - kyujinpy/KOR-OpenOrca-Platypus-v3
pipeline_tag: text-generation
license: cc-by-nc-sa-4.0

SOLAR-tail-10.7B-instruct-v1.0

Model Details

Model Developers Kyujin Han (kyujinpy)

Method
Instruction-tuning with PracticeLLM/SOLAR-tail-10.7B-Merge-v1.0.

Datasets
datasets: kyujinpy/KOR-OpenOrca-Platypus-v3.

Hyperparameters
(I will update all!)

Model Benchmark

Open leaderboard

Follow up as link.

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	Ko-CommonGenV2
PracticeLLM/SOLAR-tail-10.7B-instruct-v1.0	NaN	NaN	NaN	NaN	NaN	NaN
PracticeLLM/SOLAR-tail-10.7B-Merge-v1.0	NaN	NaN	NaN	NaN	NaN	NaN
jjourney1125/M-SOLAR-10.7B-v1.0	55.15	49.57	60.12	54.60	49.23	62.22
beomi/Yi-Ko-6B	48.79	41.04	53.39	46.28	41.64	61.63
mistralai/Mistral-7B-v0.1	46.89	38.14	48.19	45.20	46.13	56.79

Implementation Code

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

repo = "PracticeLLM/SOLAR-tail-10.7B-instruct-v1.0"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)