Edit model card

Model Card for Model ID

AI ์™€ ๋น…๋ฐ์ดํ„ฐ ๋ถ„์„ ์ „๋ฌธ ๊ธฐ์—…์ธ Linkbricks์˜ ๋ฐ์ดํ„ฐ์‚ฌ์ด์–ธํ‹ฐ์ŠคํŠธ์ธ ์ง€์œค์„ฑ(Saxo) ์ด์‚ฌ๊ฐ€ meta-llama/Meta-Llama-3-8B๋ฅผ ๋ฒ ์ด์Šค๋ชจ๋ธ๋กœ GCP์ƒ์˜ H100-80G 8๊ฐœ๋ฅผ ํ†ตํ•ด SFT-DPO ํ›ˆ๋ จ์„ ํ•œ(8000 Tokens) ํ•œ๊ธ€ ๊ธฐ๋ฐ˜ ๋ชจ๋ธ. ํ† ํฌ๋‚˜์ด์ €๋Š” ๋ผ๋งˆ3๋ž‘ ๋™์ผํ•˜๋ฉฐ ํ•œ๊ธ€ VOCA ํ™•์žฅ์€ ํ•˜์ง€ ์•Š์€ ๋ฒ„์ „ ์ž…๋‹ˆ๋‹ค. ํ•œ๊ธ€์ด 20๋งŒ๊ฐœ ์ด์ƒ ํฌํ•จ๋œ ํ•œ๊ธ€์ „์šฉ ํ† ํฌ๋‚˜์ด์ € ๋ชจ๋ธ์€ ๋ณ„๋„ ์—ฐ๋ฝ ์ฃผ์‹œ๊ธฐ ๋ฐ”๋ž๋‹ˆ๋‹ค.

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 )

Downloads last month
179
Safetensors
Model size
8.03B params
Tensor type
BF16
ยท
Inference API
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Saxo/Linkbricks-Horizon-AI-Korean-llama3-sft-dpo-8b-base

Merges
1 model
Quantizations
2 models

Dataset used to train Saxo/Linkbricks-Horizon-AI-Korean-llama3-sft-dpo-8b-base

Spaces using Saxo/Linkbricks-Horizon-AI-Korean-llama3-sft-dpo-8b-base 3