Rithankoushik/job

Rithankoushik/job-parser-model-qwen-2.0 · Hugging Face 📦 Qwen3-0.6B — Job Description Struct-Extractor A fine-tuned version of Qwen3-0.6B designed for accurate extraction of structured job attributes from raw job descriptions. Outputs perfectly schema-aligned JSON — ideal for downstream use in search, analytics, and recommendation systems. --- 🚀 Model Highlights - Base Model: Qwen/Qwen3-0.6B - Architecture: Decoder-only Transformer (Causal Language Model) - Tokenizer:`QwenTokenizer`(same as base) - Fine-Tuned For: Zero-hallucination, schema-conformant information extraction --- 🎯 Task Overview Task: Extract structured information from job descriptions Output Format: Strict JSON following a predefined schema Use Cases: - Automated JD parsing into structured fields - Building search/match systems for talent platforms - HR data cleaning & analytics pipelines - Resume/job matching engines --- 🧪 Example Usage (via transformers) ``` import torch from transformers import AutoTokenizer, AutoModelForCausalLM model_id = "Rithankoushik/job-parser-model-qwen-2.0" or your HF repo tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto") model.eval() def get_structured_jd(jd_text): system_prompt = ( "You are an expert JSON extractor specifically trained to parse job descriptions into a structured JSON format using a given schema. " "Your ONLY goal is to extract exactly and only what is explicitly stated in the job description text. " "Do NOT guess, infer, or add any information that is not mentioned. " "If a field is not present in the job description, fill it with empty or null values as specified by the schema. " "Always perfectly follow the provided JSON schema. " "Return ONLY the JSON object with no extra commentary or formatting." ) schema = '''{ "job_titles"