Downloads · 30 days
76
31% of all-time downloads
phuongntc/qwen3-0.6b-vietnamese-legal-sft
qwen3-0.6b-vietnamese-legal-sft is a text generation model from phuongntc. Use it when you need the model to write or continue text. It is set up for peft.
This repository contains the supervised fine-tuning (SFT) LoRA adapter used as the initialization policy for the CEFC-RFT Vietnamese legal summarization study.
Downloads · 30 days
76
31% of all-time downloads
All-time downloads
244
Public
Repo size
51.9 MB
Likes
4
Public
Click a slice to open those files.
.safetensors40.4 MB · 72%
From the Hugging Face model README
This repository contains the supervised fine-tuning (SFT) LoRA adapter used as the initialization policy for the CEFC-RFT Vietnamese legal summarization study.
Qwen/Qwen3-0.6B
r=16320.05q_proj, k_proj, v_proj, o_proj,
gate_proj, up_proj, down_projThis is the SFT checkpoint before reward-guided CEFC-RFT continuation. CEFC-RFT candidate generation starts from this adapter. It is not the final CEFC-RFT adapter.
Research on Vietnamese legal-document summarization and reproduction of the CEFC-RFT candidate-generation/calibration pipeline.
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base_id = "Qwen/Qwen3-0.6B"
adapter_id = "phuongntc/qwen3-0.6b-vietnamese-legal-sft"
tokenizer = AutoTokenizer.from_pretrained(base_id)
base = AutoModelForCausalLM.from_pretrained(base_id)
model = PeftModel.from_pretrained(base, adapter_id)
model.eval()