---
library_name: transformers
license: apache-2.0
basemodel: meta-llama/Meta-Llama-3-8B-Instruct
datasets:
- Saxo/total_ko_train_set_1_with_wiki_with_orca
language:
- ko
- en
pipeline_tag: text-generation
---

# Model Card for Model ID

<div align="center">
<img src="https://www.linkbricks.com/wp-content/uploads/2022/03/%E1%84%85%E1%85%B5%E1%86%BC%E1%84%8F%E1%85%B3%E1%84%87%E1%85%B3%E1%84%85%E1%85%B5%E1%86%A8%E1%84%89%E1%85%B3%E1%84%85%E1%85%A9%E1%84%80%E1%85%A9-2-1024x804.png" />
</div>


AI 와 빅데이터 분석 전문 기업인 Linkbricks의 데이터사이언티스트인 지윤성 박사(Saxo)가 meta-llama/Meta-Llama-3-8B를 베이스모델로 GCP상의 H100-60G 8개를 통해 SFT-DPO 훈련을 한(8000 Tokens) 모델.
 Accelerate, Deepspeed Zero-3 라이브러리를 사용했으며 Flash Attention 은 Disable  로 설정

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

## Configuration including BitsandBytes
---
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
)