lengocquangLAB/phobert-large-cv-skill-jd-req-match

PhoBERT Large Fine-tuned for CV-Skill to Job Description Matching

This model is a PhoBERT-Large fine-tuned with LoRA for sequence classification.
It can be used to predict if a CV skill matches a job description.

Training Details

• Base model: vinai/phobert-large
• Task: Sequence Classification (2 labels)
• LoRA config: r=16, lora_alpha=32, target_modules=["query", "key", "value", "output.dense"], lora_dropout=0.05
• Optimizer: AdamW, lr=2e-4
• Batch size: 120 (gradient accumulation 4)
• Epochs: 8
• Metrics: F1-score
• Framework: HuggingFace Transformers + PEFT

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("lengocquangLAB/phobert-large-cv-skill-jd-req-match")
model = AutoModelForSequenceClassification.from_pretrained("lengocquangLAB/phobert-large-cv-skill-jd-req-match")

inputs = tokenizer("CV skill text", "Job description text", return_tensors="pt")
outputs = model(**inputs)
pred = outputs.logits.argmax(dim=-1)
print(pred)