LLaMA3 8B — IndoSum QLoRA (Adapter)
Model ini adalah adaptor PEFT (QLoRA) yang dilatih pada dataset tuanmuda/indosum.
Gunakan bersama base model: Sahabat-AI/llama3-8b-cpt-sahabatai-v1-instruct.
Cara Pakai
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base_id = "Sahabat-AI/llama3-8b-cpt-sahabatai-v1-instruct"
adapter_id = "tuanmuda/llama3-8b-indosum-qlora-adapter"
tok = AutoTokenizer.from_pretrained(base_id)
base = AutoModelForCausalLM.from_pretrained(base_id, device_map="auto")
model = PeftModel.from_pretrained(base, adapter_id, device_map="auto")
- Downloads last month
- 2
Model tree for tuanmuda/llama3-8b-indosum-qlora-adapter
Base model
meta-llama/Meta-Llama-3-8B-Instruct Finetuned
aisingapore/Llama-SEA-LION-v2-8B Finetuned
aisingapore/Llama-SEA-LION-v2-8B-IT
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Sahabat-AI/llama3-8b-cpt-sahabatai-v1-instruct") model = PeftModel.from_pretrained(base_model, "tuanmuda/llama3-8b-indosum-qlora-adapter")