Downloads · 30 days
62
2% of all-time downloads
Saxo/Linkbricks-Horizon-AI-Korean-llama3-sft-dpo-8b-base
Linkbricks-Horizon-AI-Korean-llama3-sft-dpo-8b-base is a text generation model from Saxo. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
<div align="center" <img src="http://www.linkbricks.com/wp-content/uploads/2024/11/fulllogo.png" / </div
Downloads · 30 days
62
2% of all-time downloads
All-time downloads
3.9K
Public
Parameters
8B
56.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.gguf40.7 GB · 72%
From the Hugging Face model README
AI 와 빅데이터 분석 전문 기업인 Linkbricks의 데이터사이언티스트인 지윤성(Saxo) 이사가 meta-llama/Meta-Llama-3-8B를 베이스모델로 GCP상의 H100-80G 8개를 통해 SFT-DPO 훈련을 한(8000 Tokens) 한글 기반 모델. 토크나이저는 라마3랑 동일하며 한글 VOCA 확장은 하지 않은 버전 입니다. 한글이 20만개 이상 포함된 한글전용 토크나이저 모델은 별도 연락 주시기 바랍니다.
Dr. Yunsung Ji (Saxo), a data scientist at Linkbricks, a company specializing in AI and big data analytics, trained the meta-llama/Meta-Llama-3-8B base model on 8 H100-60Gs on GCP for 4 hours of instructional training (8000 Tokens). Accelerate, Deepspeed Zero-3 libraries were used.
www.linkbricks.com, www.linkbricks.vc
bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_use_double_quant=False, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch_dtype )
args = TrainingArguments( output_dir=project_name, run_name=run_name_str, overwrite_output_dir=True, num_train_epochs=20, per_device_train_batch_size=1, gradient_accumulation_steps=4, #1 gradient_checkpointing=True, optim="paged_adamw_32bit", #optim="adamw_8bit", logging_steps=10, save_steps=100, save_strategy="epoch", learning_rate=2e-4, #2e-4 weight_decay=0.01, max_grad_norm=1, #0.3 max_steps=-1, warmup_ratio=0.1, group_by_length=False, fp16 = not torch.cuda.is_bf16_supported(), bf16 = torch.cuda.is_bf16_supported(), #fp16 = True, lr_scheduler_type="cosine", #"constant", disable_tqdm=False, report_to='wandb', push_to_hub=False )