--- language: en license: apache-2.0 base_model: unsloth/Qwen3-4B-Thinking-2507 tags: - medical - llm - qwen3 - thinking-model - entity-extraction - relation-extraction - lora - peft library_name: transformers pipeline_tag: text-generation --- # Medical-NER-Qwen-4B-Thinking ## Model Description This is a fine-tuned medical LLM based on Qwen3-4B-Thinking, specialized for medical entity and relationship extraction. ## Model Details - **Base Model**: unsloth/Qwen3-4B-Thinking-2507 - **Fine-tuning Method**: LoRA (Low-Rank Adaptation) - **Domain**: Medical Literature Analysis - **Tasks**: Entity Recognition, Relationship Extraction - **Language**: English ## Performance Metrics | Metric | Entity Extraction | Relationship Extraction | |--------|------------------|------------------------| | Precision | 0.000 | 0.000 | | Recall | 0.000 | 0.000 | | F1-Score | 0.000 | 0.000 | ## Usage ```python from transformers import AutoTokenizer, AutoModelForCausalLM from peft import PeftModel # Load base model base_model = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen2.5-3B-Thinking", torch_dtype="auto", device_map="auto" ) # Load LoRA adapter model = PeftModel.from_pretrained(base_model, "xingqiang/Medical-NER-Qwen-4B-Thinking-merged") tokenizer = AutoTokenizer.from_pretrained("xingqiang/Medical-NER-Qwen-4B-Thinking-merged") # Generate medical analysis text = "Hepatitis C virus causes chronic liver infection." messages = [ {"role": "user", "content": f"Extract medical entities and relationships from: {text}"} ] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) inputs = tokenizer(prompt, return_tensors="pt") outputs = model.generate(**inputs, max_new_tokens=256) result = tokenizer.decode(outputs[0], skip_special_tokens=True) print(result) ```