BSVGK/gemma-1.1-2b-it-drugbank-kg2text-lora-v2

Gemma 1.1 2B IT — LoRA Adapter v2 (DrugBank KG-to-Text)

Model Summary

This is the LoRA adapter v2 for the Gemma 1.1 2B IT model fine-tuned to generate fluent, hallucination-free natural language drug descriptions from pharmaceutical RDF knowledge graph triples sourced from DrugBank. It was developed as part of a UEL–Depixen industrial placement research project focused on building trustworthy, domain-specific SLMs.

For the full merged model ready for inference, use: 👉 BSVGK/gemma-1.1-2b-it-drugbank-kg2text-merged-v2

Key Results

Metric	Score
BLEU Score	0.9737
BERTScore F1	0.9896
Fact F1	0.9966
Hallucination Rate	0.54%
Test Samples	254 unseen DrugBank entries

Model Details

• Base Model: google/gemma-1.1-2b-it
• Adapter Type: LoRA (Low-Rank Adaptation)
• Task: KG-to-Text — RDF triples → fluent drug descriptions
• Domain: Pharmaceutical — DrugBank
• Training Dataset: 2,537 verified DrugBank RDF triples
• Hardware: NVIDIA A100
• Framework: PyTorch, Hugging Face PEFT, TRL, SFTTrainer

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM from peft import PeftModel

Load base model

base_model = AutoModelForCausalLM.from_pretrained( "google/gemma-1.1-2b-it" ) tokenizer = AutoTokenizer.from_pretrained( "google/gemma-1.1-2b-it" )

Load LoRA adapter

model = PeftModel.from_pretrained( base_model, "BSVGK/gemma-1.1-2b-it-drugbank-kg2text-lora-v2" )

prompt = """Generate a natural language description from the following RDF triples:

Triples:

• DrugA hasIndication Condition_X
• DrugA hasMechanism Mechanism_Y
• DrugA hasInteraction DrugB

Description:"""

inputs = tokenizer(prompt, return_tensors="pt") outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Dataset

• Dataset: BSVGK/drugbank_dataset
• Size: 2,537 training + 254 test samples
• Source: DrugBank pharmaceutical database
• Format: RDF Triples → Natural Language Drug Description

Intended Use

• Pharmaceutical knowledge graph verbalisation
• Drug information summarisation and description generation
• Research in trustworthy and hallucination-free biomedical NLP
• Natural language generation from biomedical knowledge graphs

Out of Scope

• Non-pharmaceutical domains
• Clinical diagnosis or medical advice
• General purpose text generation

Important Notice

This model is intended for research purposes only. It should not be used for clinical decision-making or medical advice. Always consult a qualified healthcare professional.

Citation

@misc{bubathula2026drugbank_adapter, author = {Sai Venkata Gopala Krishna Bubathula}, title = {Gemma 1.1 2B IT LoRA Adapter v2: KG-to-Text Generation for DrugBank Pharmaceutical Data}, year = {2026}, publisher = {HuggingFace}, url = {https://huggingface.co/BSVGK/gemma-1.1-2b-it-drugbank-kg2text-lora-v2}, institution = {University of East London & Depixen} }

Developer

Sai Venkata Gopala Krishna Bubathula

• 🎓 MSc Big Data Technologies, University of East London

• 🏢 AI Engineer — UEL–Depixen Industrial Placement

• 🔗 GitHub

• 🔗 Merged Model

• 🔗 LinkedIn

• Adapter intended for KG-to-text generation only