Views
No views yet
google/gemma-3-27b-it trained with an IEInstruct-style named-entity-recognition only objective. Released as a general information-extraction baseline for the anonymous submission "From Lengthy Narrative to Structured Data: Instruction Fine-Tuning Open-Weight LLMs for Information Extraction from Corporate Disclosures."| Base model | google/gemma-3-27b-it |
| Method | LoRA (r=8, α=16), 4-bit QLoRA |
| Training objective | named-entity-recognition only |
| Instance-level F1 (consultant task) | 75.8% |
1from transformers import AutoModelForCausalLM, AutoTokenizer
2from peft import PeftModel
3
4base = "google/gemma-3-27b-it"
5tok = AutoTokenizer.from_pretrained(base)
6model = AutoModelForCausalLM.from_pretrained(base, device_map="auto", load_in_4bit=True)
7model = PeftModel.from_pretrained(model, "cs-file-uploads/ie-ner-adapter")1@misc{anonymous2026fromlengthy,
2 title={From Lengthy Narrative to Structured Data: Instruction Fine-Tuning Open-Weight LLMs for Information Extraction from Corporate Disclosures},
3 author={Anonymous},
4 year={2026},
5 note={Under review}
6}