satgothyun/pmsp_llama8b_lora_10000

PMSP LLaMA 8B Fine-tuned Model

Model Description

PMSP 최적화를 위해 파인튜닝된 LLaMA 8B 모델입니다.

Training Details

• Base Model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
• LoRA Rank: 64
• Epochs: 4
• Max Sequence Length: 8,192
• Dataset: ACCORD

Usage

from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="satgothyun/pmsp_llama8b_lora_10000",
    max_seq_length=8192,
    load_in_4bit=True,
    dtype=torch.bfloat16,
)
FastLanguageModel.for_inference(model)