Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
qwen2.5-0.5b-legal-rag-qlora-pgabl – AI Model by incesamsul | AlphaNeural AI
You can deploy this model and start earning money today!
incesamsul
/
qwen2.5-0.5b-legal-rag-qlora-pgabl
like
0
qlora
sft
rag
dicoding-submission
text-generation
id
Ichsan2895/alpaca-gpt4-indonesian
unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit
finetune
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Qwen2.5 0.5B Legal RAG QLoRA PGABL
Model repository for Dicoding submission Proyek Akhir Fine-tuned Chatbot Tim Legal berbasis RAG.
Fine-tuning notebook defines: QLoRA 4-bit, dataset Ichsan2895/alpaca-gpt4-indonesian, TRL SFTTrainer, max_steps=800, LoRA attention and FFN target modules.
RAG notebook loads this repository with Transformers and combines it with FAISS/BM25 retrieval, cross-encoder reranking, citations, and Gradio UI.