Sync card and scripts from the monorepo

Browse files

Files changed (4) hide show

README.md +3 -1
data_generator.py +792 -231
inference.py +58 -21
train.py +105 -43

README.md CHANGED Viewed

@@ -116,7 +116,9 @@ classifier = pipeline(
     model="gr8monk3ys/resume-section-classifier",
 )
-result = classifier("Bachelor of Science in Computer Science, Stanford University, 2023. GPA: 3.9/4.0")
 print(result)
 # [{'label': 'education', 'score': 0.98}]
 ```

     model="gr8monk3ys/resume-section-classifier",
 )
+result = classifier(
+    "Bachelor of Science in Computer Science, Stanford University, 2023. GPA: 3.9/4.0"
+)
 print(result)
 # [{'label': 'education', 'score': 0.98}]
 ```

data_generator.py CHANGED Viewed

@@ -17,51 +17,172 @@ from pathlib import Path
 # ---------------------------------------------------------------------------
 FIRST_NAMES = [
-    "James", "Mary", "Robert", "Patricia", "John", "Jennifer", "Michael",
-    "Linda", "David", "Elizabeth", "William", "Barbara", "Richard", "Susan",
-    "Joseph", "Jessica", "Thomas", "Sarah", "Charles", "Karen", "Daniel",
-    "Lisa", "Matthew", "Nancy", "Anthony", "Betty", "Mark", "Sandra",
-    "Aisha", "Wei", "Carlos", "Priya", "Olga", "Hiroshi", "Fatima", "Liam",
-    "Sofia", "Andrei", "Mei", "Alejandro", "Yuki", "Omar", "Elena", "Raj",
 ]
 LAST_NAMES = [
-    "Smith", "Johnson", "Williams", "Brown", "Jones", "Garcia", "Miller",
-    "Davis", "Rodriguez", "Martinez", "Hernandez", "Lopez", "Gonzalez",
-    "Wilson", "Anderson", "Thomas", "Taylor", "Moore", "Jackson", "Martin",
-    "Lee", "Perez", "Thompson", "White", "Harris", "Sanchez", "Clark",
-    "Patel", "Chen", "Kim", "Nakamura", "Ivanov", "Silva", "Okafor",
 ]
 COMPANIES = [
-    "Google", "Microsoft", "Amazon", "Apple", "Meta", "Netflix", "Stripe",
-    "Airbnb", "Uber", "Salesforce", "Adobe", "IBM", "Oracle", "Intel",
-    "Tesla", "SpaceX", "Palantir", "Snowflake", "Databricks", "Confluent",
-    "JPMorgan Chase", "Goldman Sachs", "Morgan Stanley", "Deloitte",
-    "McKinsey & Company", "Boston Consulting Group", "Accenture",
-    "Lockheed Martin", "Boeing", "Raytheon", "General Electric",
-    "Procter & Gamble", "Johnson & Johnson", "Pfizer", "Moderna",
-    "Shopify", "Square", "Twilio", "Cloudflare", "HashiCorp",
-    "DataRobot", "Hugging Face", "OpenAI", "Anthropic", "Cohere",
-    "Startup XYZ", "TechCorp Inc.", "InnovateTech", "DataDriven LLC",
 ]
 UNIVERSITIES = [
-    "Massachusetts Institute of Technology", "Stanford University",
-    "Harvard University", "University of California, Berkeley",
-    "Carnegie Mellon University", "Georgia Institute of Technology",
-    "University of Michigan", "University of Illinois Urbana-Champaign",
-    "California Institute of Technology", "Princeton University",
-    "Columbia University", "University of Washington",
-    "University of Texas at Austin", "Cornell University",
-    "University of Pennsylvania", "University of Southern California",
-    "New York University", "University of Wisconsin-Madison",
-    "Duke University", "Northwestern University",
-    "University of California, Los Angeles", "Rice University",
-    "University of Maryland", "Purdue University",
-    "Ohio State University", "Arizona State University",
-    "University of Virginia", "University of Florida",
-    "Boston University", "Northeastern University",
 ]
 DEGREES = [
@@ -77,78 +198,216 @@ DEGREES = [
 ]
 MAJORS = [
-    "Computer Science", "Software Engineering", "Data Science",
-    "Electrical Engineering", "Mechanical Engineering",
-    "Information Technology", "Mathematics", "Statistics",
-    "Business Administration", "Economics", "Finance",
-    "Biomedical Engineering", "Chemical Engineering",
-    "Civil Engineering", "Physics", "Biology",
-    "Artificial Intelligence", "Machine Learning",
-    "Human-Computer Interaction", "Cybersecurity",
-    "Information Systems", "Operations Research",
 ]
 MINORS = [
-    "Mathematics", "Statistics", "Psychology", "Business",
-    "Economics", "Philosophy", "Linguistics", "Physics",
-    "Data Science", "Communication", "Sociology", "History",
 ]
 GPA_VALUES = [
-    "3.5", "3.6", "3.7", "3.8", "3.9", "4.0",
-    "3.52", "3.65", "3.78", "3.85", "3.92", "3.45",
 ]
 GRAD_YEARS = list(range(2015, 2027))
 JOB_TITLES = [
-    "Software Engineer", "Senior Software Engineer", "Staff Engineer",
-    "Principal Engineer", "Engineering Manager", "Tech Lead",
-    "Data Scientist", "Senior Data Scientist", "Machine Learning Engineer",
-    "ML Research Scientist", "Data Engineer", "Data Analyst",
-    "Product Manager", "Senior Product Manager", "Program Manager",
-    "DevOps Engineer", "Site Reliability Engineer", "Cloud Architect",
-    "Full Stack Developer", "Frontend Engineer", "Backend Engineer",
-    "Mobile Developer", "iOS Engineer", "Android Developer",
-    "QA Engineer", "Security Engineer", "Solutions Architect",
-    "Research Scientist", "AI Engineer", "NLP Engineer",
-    "Quantitative Analyst", "Financial Analyst", "Business Analyst",
-    "UX Designer", "UI Engineer", "Technical Writer",
-    "Intern", "Software Engineering Intern", "Data Science Intern",
 ]
 PROGRAMMING_LANGUAGES = [
-    "Python", "Java", "JavaScript", "TypeScript", "C++", "C", "C#",
-    "Go", "Rust", "Kotlin", "Swift", "Ruby", "PHP", "Scala",
-    "R", "MATLAB", "Julia", "Haskell", "Elixir", "Dart",
 ]
 FRAMEWORKS = [
-    "React", "Angular", "Vue.js", "Next.js", "Django", "Flask",
-    "FastAPI", "Spring Boot", "Express.js", "Node.js", "Rails",
-    "TensorFlow", "PyTorch", "Keras", "scikit-learn", "Pandas",
-    "NumPy", "Spark", "Hadoop", "Kubernetes", "Docker",
-    "AWS", "GCP", "Azure", "Terraform", "Ansible",
-    ".NET", "Laravel", "Svelte", "Remix", "Astro",
 ]
 TOOLS = [
-    "Git", "GitHub", "GitLab", "Jira", "Confluence", "Slack",
-    "VS Code", "IntelliJ", "PyCharm", "Vim", "Emacs",
-    "PostgreSQL", "MySQL", "MongoDB", "Redis", "Elasticsearch",
-    "Kafka", "RabbitMQ", "Airflow", "dbt", "Snowflake",
-    "Tableau", "Power BI", "Grafana", "Prometheus", "Datadog",
-    "Jenkins", "CircleCI", "GitHub Actions", "ArgoCD",
-    "Figma", "Sketch", "Adobe XD", "Postman", "Swagger",
 ]
 SOFT_SKILLS = [
-    "Leadership", "Communication", "Team Collaboration",
-    "Problem Solving", "Critical Thinking", "Time Management",
-    "Project Management", "Agile Methodologies", "Scrum",
-    "Cross-functional Collaboration", "Mentoring",
-    "Strategic Planning", "Stakeholder Management",
-    "Technical Writing", "Public Speaking", "Negotiation",
 ]
 CERTIFICATIONS_LIST = [
@@ -178,47 +437,120 @@ CERTIFICATIONS_LIST = [
 ]
 AWARDS_LIST = [
-    "Dean's List", "Summa Cum Laude", "Magna Cum Laude", "Cum Laude",
-    "Phi Beta Kappa", "Tau Beta Pi", "National Merit Scholar",
-    "Employee of the Quarter", "Spot Bonus Award", "President's Club",
-    "Best Paper Award", "Innovation Award", "Hackathon Winner",
-    "Outstanding Graduate Student Award", "Research Fellowship",
-    "Teaching Assistant Excellence Award", "Community Service Award",
-    "IEEE Best Student Paper", "ACM ICPC Regional Finalist",
-    "Google Code Jam Qualifier", "Facebook Hacker Cup Participant",
-    "Patent Holder", "Top Performer Award", "Rising Star Award",
 ]
 CITIES = [
-    "San Francisco, CA", "New York, NY", "Seattle, WA", "Austin, TX",
-    "Boston, MA", "Chicago, IL", "Los Angeles, CA", "Denver, CO",
-    "Portland, OR", "Atlanta, GA", "Washington, DC", "San Jose, CA",
-    "Raleigh, NC", "Pittsburgh, PA", "Minneapolis, MN", "Dallas, TX",
-    "Miami, FL", "Phoenix, AZ", "San Diego, CA", "Philadelphia, PA",
 ]
 MONTHS = [
-    "January", "February", "March", "April", "May", "June",
-    "July", "August", "September", "October", "November", "December",
 ]
 MONTHS_SHORT = [
-    "Jan", "Feb", "Mar", "Apr", "May", "Jun",
-    "Jul", "Aug", "Sep", "Oct", "Nov", "Dec",
 ]
 PROJECT_ADJECTIVES = [
-    "Real-time", "Scalable", "Distributed", "Cloud-native",
-    "AI-powered", "Automated", "Interactive", "Cross-platform",
-    "Open-source", "End-to-end", "High-performance", "Serverless",
-    "Event-driven", "Microservice-based", "Full-stack",
 ]
 PROJECT_NOUNS = [
-    "Dashboard", "Platform", "Pipeline", "Application", "System",
-    "API", "Framework", "Tool", "Service", "Engine",
-    "Chatbot", "Recommendation System", "Search Engine",
-    "Analytics Platform", "Monitoring System", "Marketplace",
 ]
 IMPACT_METRICS = [
@@ -239,21 +571,42 @@ IMPACT_METRICS = [
 ]
 PHONE_AREA_CODES = [
-    "415", "650", "408", "510", "212", "646", "718", "206",
-    "512", "617", "312", "213", "303", "503", "404", "202",
 ]
 LINKEDIN_PREFIXES = [
-    "linkedin.com/in/", "www.linkedin.com/in/",
 ]
 GITHUB_PREFIXES = [
-    "github.com/", "www.github.com/",
 ]
 DOMAINS = [
-    "gmail.com", "outlook.com", "yahoo.com", "protonmail.com",
-    "icloud.com", "hotmail.com", "mail.com",
 ]
 # ---------------------------------------------------------------------------
@@ -261,12 +614,53 @@ DOMAINS = [
 # ---------------------------------------------------------------------------
 SYNONYMS = {
-    "developed": ["built", "created", "engineered", "designed", "implemented", "constructed", "authored"],
-    "managed": ["led", "oversaw", "directed", "supervised", "coordinated", "administered"],
-    "improved": ["enhanced", "optimized", "upgraded", "refined", "boosted", "strengthened"],
-    "implemented": ["deployed", "executed", "delivered", "rolled out", "launched", "shipped"],
-    "analyzed": ["examined", "evaluated", "assessed", "investigated", "studied", "reviewed"],
-    "collaborated": ["partnered", "worked closely with", "teamed up with", "cooperated with"],
     "responsible for": ["in charge of", "accountable for", "tasked with", "owned"],
     "utilized": ["leveraged", "employed", "used", "applied", "harnessed"],
     "achieved": ["accomplished", "attained", "reached", "secured", "delivered"],
@@ -278,6 +672,7 @@ SYNONYMS = {
 # Helper utilities
 # ---------------------------------------------------------------------------
 def _pick(pool, k=1):
     """Return k unique random items from a pool."""
     k = min(k, len(pool))
@@ -342,7 +737,7 @@ def _synonym_replace(text: str) -> str:
             if w[0].isupper():
                 replacement = replacement.capitalize()
             # Preserve trailing punctuation
-            trailing = w[len(lower):]
             result.append(replacement + trailing)
         else:
             result.append(w)
@@ -365,6 +760,7 @@ def _reorder_bullets(bullets: list) -> list:
 # Section generators – each returns a string of realistic text
 # ---------------------------------------------------------------------------
 def generate_education() -> str:
     """Generate a realistic education section."""
     templates = []
@@ -399,34 +795,56 @@ def generate_education() -> str:
         # Optional coursework
         if random.random() < 0.5:
-            courses = _pick(MAJORS + ["Algorithms", "Data Structures",
-                                       "Operating Systems", "Database Systems",
-                                       "Computer Networks", "Linear Algebra",
-                                       "Probability and Statistics",
-                                       "Deep Learning", "Natural Language Processing",
-                                       "Computer Vision", "Distributed Systems"], k=random.randint(3, 6))
-            prefix = random.choice(["Relevant Coursework:", "Key Courses:", "Coursework:"])
             lines.append(f"{prefix} {', '.join(courses)}")
         # Optional honors
         if random.random() < 0.3:
-            honor = random.choice(["Summa Cum Laude", "Magna Cum Laude",
-                                    "Cum Laude", "Dean's List (all semesters)",
-                                    "Honors Program", "University Scholar"])
             lines.append(honor)
         # Optional thesis
         if "Ph.D." in deg_short or ("M.S." in deg_short and random.random() < 0.4):
-            topic = random.choice([
-                "Transformer-based approaches to document classification",
-                "Scalable distributed systems for real-time data processing",
-                "Graph neural networks for molecular property prediction",
-                "Federated learning in healthcare applications",
-                "Efficient attention mechanisms for long-sequence modeling",
-                "Reinforcement learning for autonomous navigation",
-            ])
             label = "Dissertation" if "Ph.D." in deg_short else "Thesis"
-            lines.append(f"{label}: \"{topic}\"")
         return "\n".join(lines)
@@ -438,7 +856,9 @@ def generate_education() -> str:
             deg_full, deg_short = _pick_one(DEGREES)
             major = _pick_one(MAJORS)
             year = _pick_one(GRAD_YEARS)
-            gpa_line = f" | GPA: {_pick_one(GPA_VALUES)}" if random.random() < 0.5 else ""
             entries.append(f"{deg_short} in {major}, {uni}, {year}{gpa_line}")
         return "\n".join(entries)
@@ -450,18 +870,21 @@ def generate_education() -> str:
         year = _pick_one(GRAD_YEARS)
         lines = [f"{uni}", f"{deg_full} in {major} | {_pick_one(MONTHS)} {year}"]
-        activities = random.sample([
-            "Teaching Assistant for Introduction to Computer Science",
-            "President, Computer Science Student Association",
-            "Member, ACM Student Chapter",
-            "Undergraduate Research Assistant, ML Lab",
-            "Peer Tutor, Mathematics Department",
-            "Captain, University Programming Competition Team",
-            "Volunteer, Engineering Outreach Program",
-            "Member, Honors College",
-            "Study Abroad Program, Technical University of Munich",
-            "Resident Advisor, Engineering Living-Learning Community",
-        ], k=random.randint(1, 3))
         b = _bullet()
         for a in activities:
@@ -492,11 +915,11 @@ def generate_experience() -> str:
         # Generate bullet points
         bullet_templates = [
-            f"Developed and maintained {random.choice(['microservices', 'APIs', 'web applications', 'data pipelines', 'ML models', 'backend systems', 'frontend components'])} using {', '.join(_pick(PROGRAMMING_LANGUAGES, k=random.randint(1,3)))} and {', '.join(_pick(FRAMEWORKS, k=random.randint(1,2)))}",
-            f"Collaborated with cross-functional teams of {random.randint(3,15)} engineers to deliver {random.choice(['product features', 'platform improvements', 'system migrations', 'infrastructure upgrades'])} on schedule",
             f"Designed and implemented {random.choice(['CI/CD pipelines', 'testing frameworks', 'monitoring solutions', 'data models', 'caching strategies', 'authentication systems'])} that {_impact()}",
             f"Led migration of {random.choice(['legacy monolith', 'on-premise infrastructure', 'batch processing system', 'manual workflows'])} to {random.choice(['cloud-native architecture', 'microservices', 'real-time streaming', 'automated pipelines'])}",
-            f"Mentored {random.randint(2,8)} junior engineers through code reviews, pair programming, and technical design sessions",
             f"Optimized {random.choice(['database queries', 'API response times', 'model inference', 'data processing pipelines', 'search indexing'])} resulting in {_impact()}",
             f"Wrote comprehensive technical documentation and {random.choice(['RFCs', 'design docs', 'runbooks', 'architecture decision records'])} for {random.choice(['system design', 'API contracts', 'deployment procedures', 'incident response'])}",
             f"Built {random.choice(['real-time', 'batch', 'streaming', 'event-driven'])} {random.choice(['data pipeline', 'ETL process', 'analytics system', 'feature store'])} processing {random.choice(['1M+', '10M+', '100M+', '1B+'])} records {random.choice(['daily', 'per hour', 'in real-time'])}",
@@ -506,7 +929,9 @@ def generate_experience() -> str:
         ]
         n_bullets = random.randint(2, 5)
-        selected = random.sample(bullet_templates, min(n_bullets, len(bullet_templates)))
         selected = _reorder_bullets(selected)
         b = _bullet()
         for bullet in selected:
@@ -535,7 +960,9 @@ def generate_skills() -> str:
         if random.random() < 0.9:
             fws = _pick(FRAMEWORKS, k=random.randint(3, 7))
-            label = random.choice(["Frameworks", "Frameworks & Libraries", "Technologies"])
             categories.append((label, fws))
         if random.random() < 0.8:
@@ -556,9 +983,11 @@ def generate_skills() -> str:
         return "\n".join(lines)
     def _t_flat():
-        all_skills = (_pick(PROGRAMMING_LANGUAGES, k=random.randint(3, 6)) +
-                      _pick(FRAMEWORKS, k=random.randint(3, 6)) +
-                      _pick(TOOLS, k=random.randint(2, 4)))
         random.shuffle(all_skills)
         joiner = random.choice([", ", " | ", " · ", " • "])
         return joiner.join(all_skills)
@@ -568,7 +997,9 @@ def generate_skills() -> str:
         levels = ["Expert", "Advanced", "Proficient", "Intermediate", "Familiar"]
         used = set()
         for level in random.sample(levels, k=random.randint(2, 4)):
-            pool = [s for s in PROGRAMMING_LANGUAGES + FRAMEWORKS + TOOLS if s not in used]
             items = _pick(pool, k=random.randint(2, 5))
             used.update(items)
             lines.append(f"{level}: {', '.join(items)}")
@@ -621,28 +1052,45 @@ def generate_projects() -> str:
 def generate_summary() -> str:
     """Generate a realistic professional summary / objective section."""
     years = random.randint(2, 15)
-    specialties = _pick(MAJORS + [
-        "full-stack development", "distributed systems", "machine learning",
-        "data engineering", "cloud architecture", "mobile development",
-        "DevOps", "backend development", "frontend development",
-        "natural language processing", "computer vision",
-    ], k=random.randint(1, 3))
     templates = [
         # Template 1: Traditional summary
-        lambda: f"Results-driven {_pick_one(JOB_TITLES).lower()} with {years}+ years of experience in {' and '.join(specialties)}. Proven track record of {random.choice(['delivering high-impact solutions', 'building scalable systems', 'driving technical excellence', 'leading cross-functional teams'])} at companies like {_pick_one(COMPANIES)} and {_pick_one(COMPANIES)}. Passionate about {random.choice(['clean code', 'system design', 'open source', 'mentorship', 'continuous learning', 'innovation'])} and {random.choice(['building products that scale', 'solving complex problems', 'leveraging data-driven insights', 'improving developer experience'])}.",
         # Template 2: Technical focus
-        lambda: f"Experienced {_pick_one(JOB_TITLES).lower()} specializing in {', '.join(specialties)}. Skilled in {', '.join(_pick(PROGRAMMING_LANGUAGES, k=3))} with deep expertise in {', '.join(_pick(FRAMEWORKS, k=2))}. {random.choice(['Strong background in', 'Demonstrated ability in', 'Track record of'])} {random.choice(['building distributed systems at scale', 'developing ML models for production', 'architecting cloud-native applications', 'leading agile engineering teams'])}. Seeking to {random.choice(['contribute to cutting-edge products', 'drive technical innovation', 'solve challenging problems', 'build impactful technology'])} at a {random.choice(['fast-growing startup', 'leading technology company', 'mission-driven organization'])}.",
         # Template 3: Achievement-oriented
-        lambda: f"{_pick_one(JOB_TITLES)} with {years} years of experience building {random.choice(['enterprise-scale', 'consumer-facing', 'B2B', 'data-intensive'])} applications. Key achievements include {_impact()}, {_impact()}, and {_impact()}. Proficient in {', '.join(_pick(PROGRAMMING_LANGUAGES, k=3))} and {', '.join(_pick(FRAMEWORKS, k=2))}.",
         # Template 4: Brief objective
-        lambda: f"Motivated {random.choice(['professional', 'engineer', 'developer', 'technologist'])} seeking a {_pick_one(JOB_TITLES).lower()} role where I can apply my expertise in {' and '.join(specialties)} to {random.choice(['build innovative products', 'solve real-world problems', 'drive business impact', 'push the boundaries of technology'])}.",
         # Template 5: Narrative style
-        lambda: f"I am a {_pick_one(JOB_TITLES).lower()} who thrives at the intersection of {_pick_one(specialties)} and {_pick_one(specialties)}. Over the past {years} years, I have {random.choice(['shipped products used by millions', 'built ML systems processing petabytes of data', 'led engineering teams through rapid growth', 'contributed to open-source projects with thousands of stars'])}. I bring a {random.choice(['data-driven', 'user-centric', 'systems-thinking', 'first-principles'])} approach to every problem I tackle.",
     ]
     return random.choice(templates)()
@@ -660,9 +1108,11 @@ def generate_certifications() -> str:
             f"{cert} ({year})",
             f"{cert} — Issued {_pick_one(MONTHS)} {year}",
             f"{cert}, {year}",
-            f"{cert}\n  Issued: {_pick_one(MONTHS_SHORT)} {year}" + (
                 f" | Expires: {_pick_one(MONTHS_SHORT)} {year + random.randint(2, 3)}"
-                if random.random() < 0.3 else ""
             ),
         ]
         lines.append(random.choice(styles))
@@ -679,15 +1129,17 @@ def generate_contact() -> str:
     last = _pick_one(LAST_NAMES)
     city = _pick_one(CITIES)
     area_code = _pick_one(PHONE_AREA_CODES)
-    email_user = random.choice([
-        f"{first.lower()}.{last.lower()}",
-        f"{first.lower()}{last.lower()}",
-        f"{first[0].lower()}{last.lower()}",
-        f"{first.lower()}_{last.lower()}",
-        f"{first.lower()}{random.randint(1, 99)}",
-    ])
     email = f"{email_user}@{_pick_one(DOMAINS)}"
-    phone = f"({area_code}) {random.randint(100,999)}-{random.randint(1000,9999)}"
     linkedin_user = f"{first.lower()}-{last.lower()}-{random.randint(100, 999)}"
     github_user = f"{first.lower()}{last.lower()}"
@@ -704,7 +1156,11 @@ def generate_contact() -> str:
     if random.random() < 0.4:
         parts.append(f"{_pick_one(GITHUB_PREFIXES)}{github_user}")
     if random.random() < 0.2:
-        parts.append(f"{github_user}.dev" if random.random() < 0.5 else f"{first.lower()}{last.lower()}.com")
     sep = random.choice(["\n", " | ", " · ", "\n"])
     return sep.join(parts)
@@ -718,12 +1174,23 @@ def generate_awards() -> str:
     for award in awards:
         year = random.randint(2015, 2025)
-        org = random.choice([
-            _pick_one(UNIVERSITIES),
-            _pick_one(COMPANIES),
-            random.choice(["ACM", "IEEE", "Google", "Facebook", "Microsoft",
-                          "National Science Foundation", "Department of Education"]),
-        ])
         styles = [
             f"{award}, {org} ({year})",
             f"{award} — {org}, {year}",
@@ -743,14 +1210,77 @@ def generate_awards() -> str:
 # ---------------------------------------------------------------------------
 SECTION_HEADERS = {
-    "education": ["EDUCATION", "Education", "Academic Background", "ACADEMIC BACKGROUND", "Education & Training"],
-    "experience": ["EXPERIENCE", "Experience", "WORK EXPERIENCE", "Work Experience", "PROFESSIONAL EXPERIENCE", "Professional Experience", "Employment History"],
-    "skills": ["SKILLS", "Skills", "TECHNICAL SKILLS", "Technical Skills", "Core Competencies", "CORE COMPETENCIES", "Technologies"],
-    "projects": ["PROJECTS", "Projects", "PERSONAL PROJECTS", "Personal Projects", "SIDE PROJECTS", "Selected Projects", "Portfolio"],
-    "summary": ["SUMMARY", "Summary", "PROFESSIONAL SUMMARY", "Professional Summary", "OBJECTIVE", "Objective", "PROFILE", "Profile", "About Me", "ABOUT"],
-    "certifications": ["CERTIFICATIONS", "Certifications", "CERTIFICATES", "Certificates", "Licenses & Certifications", "PROFESSIONAL CERTIFICATIONS"],
-    "contact": ["CONTACT", "Contact", "CONTACT INFORMATION", "Contact Information", "Personal Information"],
-    "awards": ["AWARDS", "Awards", "HONORS & AWARDS", "Honors & Awards", "ACHIEVEMENTS", "Achievements", "Awards & Honors", "RECOGNITION"],
 }
 GENERATORS = {
@@ -769,7 +1299,10 @@ GENERATORS = {
 # Dataset generation
 # ---------------------------------------------------------------------------
-def generate_example(label: str, include_header: bool = False, augment: bool = False) -> str:
     """
     Generate a single synthetic example for the given label.
@@ -832,7 +1365,9 @@ def generate_dataset(
             # Generate augmented versions
             for _ in range(augmented_copies):
-                aug_text = generate_example(label, include_header=include_header, augment=True)
                 dataset.append({"text": aug_text, "label": label})
     random.shuffle(dataset)
@@ -865,7 +1400,9 @@ def load_as_hf_dataset(dataset: list[dict]):
     # 80/10/10 split, stratified at both steps
     train_test = ds.train_test_split(test_size=0.2, seed=42, stratify_by_column="label")
-    val_test = train_test["test"].train_test_split(test_size=0.5, seed=42, stratify_by_column="label")
     # Decode ids back to names. Casting ClassLabel -> string does NOT do this
     # (it stringifies the ids, giving "0"/"1"), and mapping into a column that
@@ -881,10 +1418,12 @@ def load_as_hf_dataset(dataset: list[dict]):
         "validation": val_test["train"],
         "test": val_test["test"],
     }
-    return DatasetDict({
-        name: split.map(to_label_name, batched=True, features=string_features)
-        for name, split in splits.items()
-    })
 def get_label_mapping(dataset: list[dict]) -> tuple[dict, dict]:
@@ -902,25 +1441,46 @@ def get_label_mapping(dataset: list[dict]) -> tuple[dict, dict]:
 if __name__ == "__main__":
     import argparse
-    parser = argparse.ArgumentParser(description="Generate synthetic resume section data")
-    parser.add_argument("--examples-per-category", type=int, default=80,
-                        help="Number of base examples per category (default: 80)")
-    parser.add_argument("--augmented-copies", type=int, default=2,
-                        help="Number of augmented copies per example (default: 2)")
-    parser.add_argument("--output", type=str, default="data/resume_sections.csv",
-                        help="Output CSV path (default: data/resume_sections.csv)")
-    parser.add_argument("--seed", type=int, default=42,
-                        help="Random seed (default: 42)")
-    parser.add_argument("--print-stats", action="store_true",
-                        help="Print dataset statistics")
-    parser.add_argument("--print-samples", type=int, default=0,
-                        help="Print N sample examples")
     args = parser.parse_args()
-    print(f"Generating dataset with {args.examples_per_category} base examples per category...")
     print(f"Augmented copies per example: {args.augmented_copies}")
-    print(f"Total expected examples: {args.examples_per_category * (1 + args.augmented_copies) * 8}")
     dataset = generate_dataset(
         examples_per_category=args.examples_per_category,
@@ -932,6 +1492,7 @@ if __name__ == "__main__":
     if args.print_stats:
         from collections import Counter
         counts = Counter(d["label"] for d in dataset)
         print("\nDataset Statistics:")
         print(f"  Total examples: {len(dataset)}")
@@ -942,11 +1503,11 @@ if __name__ == "__main__":
         print(f"  Average text length: {avg_len:.0f} chars")
     if args.print_samples > 0:
-        print(f"\n{'='*60}")
         print(f"Sample Examples (first {args.print_samples}):")
-        print(f"{'='*60}")
-        for i, example in enumerate(dataset[:args.print_samples]):
-            print(f"\n--- Example {i+1} [{example['label']}] ---")
             print(example["text"][:300])
             if len(example["text"]) > 300:
                 print("...")

 # ---------------------------------------------------------------------------
 FIRST_NAMES = [
+    "James",
+    "Mary",
+    "Robert",
+    "Patricia",
+    "John",
+    "Jennifer",
+    "Michael",
+    "Linda",
+    "David",
+    "Elizabeth",
+    "William",
+    "Barbara",
+    "Richard",
+    "Susan",
+    "Joseph",
+    "Jessica",
+    "Thomas",
+    "Sarah",
+    "Charles",
+    "Karen",
+    "Daniel",
+    "Lisa",
+    "Matthew",
+    "Nancy",
+    "Anthony",
+    "Betty",
+    "Mark",
+    "Sandra",
+    "Aisha",
+    "Wei",
+    "Carlos",
+    "Priya",
+    "Olga",
+    "Hiroshi",
+    "Fatima",
+    "Liam",
+    "Sofia",
+    "Andrei",
+    "Mei",
+    "Alejandro",
+    "Yuki",
+    "Omar",
+    "Elena",
+    "Raj",
 ]
 LAST_NAMES = [
+    "Smith",
+    "Johnson",
+    "Williams",
+    "Brown",
+    "Jones",
+    "Garcia",
+    "Miller",
+    "Davis",
+    "Rodriguez",
+    "Martinez",
+    "Hernandez",
+    "Lopez",
+    "Gonzalez",
+    "Wilson",
+    "Anderson",
+    "Thomas",
+    "Taylor",
+    "Moore",
+    "Jackson",
+    "Martin",
+    "Lee",
+    "Perez",
+    "Thompson",
+    "White",
+    "Harris",
+    "Sanchez",
+    "Clark",
+    "Patel",
+    "Chen",
+    "Kim",
+    "Nakamura",
+    "Ivanov",
+    "Silva",
+    "Okafor",
 ]
 COMPANIES = [
+    "Google",
+    "Microsoft",
+    "Amazon",
+    "Apple",
+    "Meta",
+    "Netflix",
+    "Stripe",
+    "Airbnb",
+    "Uber",
+    "Salesforce",
+    "Adobe",
+    "IBM",
+    "Oracle",
+    "Intel",
+    "Tesla",
+    "SpaceX",
+    "Palantir",
+    "Snowflake",
+    "Databricks",
+    "Confluent",
+    "JPMorgan Chase",
+    "Goldman Sachs",
+    "Morgan Stanley",
+    "Deloitte",
+    "McKinsey & Company",
+    "Boston Consulting Group",
+    "Accenture",
+    "Lockheed Martin",
+    "Boeing",
+    "Raytheon",
+    "General Electric",
+    "Procter & Gamble",
+    "Johnson & Johnson",
+    "Pfizer",
+    "Moderna",
+    "Shopify",
+    "Square",
+    "Twilio",
+    "Cloudflare",
+    "HashiCorp",
+    "DataRobot",
+    "Hugging Face",
+    "OpenAI",
+    "Anthropic",
+    "Cohere",
+    "Startup XYZ",
+    "TechCorp Inc.",
+    "InnovateTech",
+    "DataDriven LLC",
 ]
 UNIVERSITIES = [
+    "Massachusetts Institute of Technology",
+    "Stanford University",
+    "Harvard University",
+    "University of California, Berkeley",
+    "Carnegie Mellon University",
+    "Georgia Institute of Technology",
+    "University of Michigan",
+    "University of Illinois Urbana-Champaign",
+    "California Institute of Technology",
+    "Princeton University",
+    "Columbia University",
+    "University of Washington",
+    "University of Texas at Austin",
+    "Cornell University",
+    "University of Pennsylvania",
+    "University of Southern California",
+    "New York University",
+    "University of Wisconsin-Madison",
+    "Duke University",
+    "Northwestern University",
+    "University of California, Los Angeles",
+    "Rice University",
+    "University of Maryland",
+    "Purdue University",
+    "Ohio State University",
+    "Arizona State University",
+    "University of Virginia",
+    "University of Florida",
+    "Boston University",
+    "Northeastern University",
 ]
 DEGREES = [
 ]
 MAJORS = [
+    "Computer Science",
+    "Software Engineering",
+    "Data Science",
+    "Electrical Engineering",
+    "Mechanical Engineering",
+    "Information Technology",
+    "Mathematics",
+    "Statistics",
+    "Business Administration",
+    "Economics",
+    "Finance",
+    "Biomedical Engineering",
+    "Chemical Engineering",
+    "Civil Engineering",
+    "Physics",
+    "Biology",
+    "Artificial Intelligence",
+    "Machine Learning",
+    "Human-Computer Interaction",
+    "Cybersecurity",
+    "Information Systems",
+    "Operations Research",
 ]
 MINORS = [
+    "Mathematics",
+    "Statistics",
+    "Psychology",
+    "Business",
+    "Economics",
+    "Philosophy",
+    "Linguistics",
+    "Physics",
+    "Data Science",
+    "Communication",
+    "Sociology",
+    "History",
 ]
 GPA_VALUES = [
+    "3.5",
+    "3.6",
+    "3.7",
+    "3.8",
+    "3.9",
+    "4.0",
+    "3.52",
+    "3.65",
+    "3.78",
+    "3.85",
+    "3.92",
+    "3.45",
 ]
 GRAD_YEARS = list(range(2015, 2027))
 JOB_TITLES = [
+    "Software Engineer",
+    "Senior Software Engineer",
+    "Staff Engineer",
+    "Principal Engineer",
+    "Engineering Manager",
+    "Tech Lead",
+    "Data Scientist",
+    "Senior Data Scientist",
+    "Machine Learning Engineer",
+    "ML Research Scientist",
+    "Data Engineer",
+    "Data Analyst",
+    "Product Manager",
+    "Senior Product Manager",
+    "Program Manager",
+    "DevOps Engineer",
+    "Site Reliability Engineer",
+    "Cloud Architect",
+    "Full Stack Developer",
+    "Frontend Engineer",
+    "Backend Engineer",
+    "Mobile Developer",
+    "iOS Engineer",
+    "Android Developer",
+    "QA Engineer",
+    "Security Engineer",
+    "Solutions Architect",
+    "Research Scientist",
+    "AI Engineer",
+    "NLP Engineer",
+    "Quantitative Analyst",
+    "Financial Analyst",
+    "Business Analyst",
+    "UX Designer",
+    "UI Engineer",
+    "Technical Writer",
+    "Intern",
+    "Software Engineering Intern",
+    "Data Science Intern",
 ]
 PROGRAMMING_LANGUAGES = [
+    "Python",
+    "Java",
+    "JavaScript",
+    "TypeScript",
+    "C++",
+    "C",
+    "C#",
+    "Go",
+    "Rust",
+    "Kotlin",
+    "Swift",
+    "Ruby",
+    "PHP",
+    "Scala",
+    "R",
+    "MATLAB",
+    "Julia",
+    "Haskell",
+    "Elixir",
+    "Dart",
 ]
 FRAMEWORKS = [
+    "React",
+    "Angular",
+    "Vue.js",
+    "Next.js",
+    "Django",
+    "Flask",
+    "FastAPI",
+    "Spring Boot",
+    "Express.js",
+    "Node.js",
+    "Rails",
+    "TensorFlow",
+    "PyTorch",
+    "Keras",
+    "scikit-learn",
+    "Pandas",
+    "NumPy",
+    "Spark",
+    "Hadoop",
+    "Kubernetes",
+    "Docker",
+    "AWS",
+    "GCP",
+    "Azure",
+    "Terraform",
+    "Ansible",
+    ".NET",
+    "Laravel",
+    "Svelte",
+    "Remix",
+    "Astro",
 ]
 TOOLS = [
+    "Git",
+    "GitHub",
+    "GitLab",
+    "Jira",
+    "Confluence",
+    "Slack",
+    "VS Code",
+    "IntelliJ",
+    "PyCharm",
+    "Vim",
+    "Emacs",
+    "PostgreSQL",
+    "MySQL",
+    "MongoDB",
+    "Redis",
+    "Elasticsearch",
+    "Kafka",
+    "RabbitMQ",
+    "Airflow",
+    "dbt",
+    "Snowflake",
+    "Tableau",
+    "Power BI",
+    "Grafana",
+    "Prometheus",
+    "Datadog",
+    "Jenkins",
+    "CircleCI",
+    "GitHub Actions",
+    "ArgoCD",
+    "Figma",
+    "Sketch",
+    "Adobe XD",
+    "Postman",
+    "Swagger",
 ]
 SOFT_SKILLS = [
+    "Leadership",
+    "Communication",
+    "Team Collaboration",
+    "Problem Solving",
+    "Critical Thinking",
+    "Time Management",
+    "Project Management",
+    "Agile Methodologies",
+    "Scrum",
+    "Cross-functional Collaboration",
+    "Mentoring",
+    "Strategic Planning",
+    "Stakeholder Management",
+    "Technical Writing",
+    "Public Speaking",
+    "Negotiation",
 ]
 CERTIFICATIONS_LIST = [
 ]
 AWARDS_LIST = [
+    "Dean's List",
+    "Summa Cum Laude",
+    "Magna Cum Laude",
+    "Cum Laude",
+    "Phi Beta Kappa",
+    "Tau Beta Pi",
+    "National Merit Scholar",
+    "Employee of the Quarter",
+    "Spot Bonus Award",
+    "President's Club",
+    "Best Paper Award",
+    "Innovation Award",
+    "Hackathon Winner",
+    "Outstanding Graduate Student Award",
+    "Research Fellowship",
+    "Teaching Assistant Excellence Award",
+    "Community Service Award",
+    "IEEE Best Student Paper",
+    "ACM ICPC Regional Finalist",
+    "Google Code Jam Qualifier",
+    "Facebook Hacker Cup Participant",
+    "Patent Holder",
+    "Top Performer Award",
+    "Rising Star Award",
 ]
 CITIES = [
+    "San Francisco, CA",
+    "New York, NY",
+    "Seattle, WA",
+    "Austin, TX",
+    "Boston, MA",
+    "Chicago, IL",
+    "Los Angeles, CA",
+    "Denver, CO",
+    "Portland, OR",
+    "Atlanta, GA",
+    "Washington, DC",
+    "San Jose, CA",
+    "Raleigh, NC",
+    "Pittsburgh, PA",
+    "Minneapolis, MN",
+    "Dallas, TX",
+    "Miami, FL",
+    "Phoenix, AZ",
+    "San Diego, CA",
+    "Philadelphia, PA",
 ]
 MONTHS = [
+    "January",
+    "February",
+    "March",
+    "April",
+    "May",
+    "June",
+    "July",
+    "August",
+    "September",
+    "October",
+    "November",
+    "December",
 ]
 MONTHS_SHORT = [
+    "Jan",
+    "Feb",
+    "Mar",
+    "Apr",
+    "May",
+    "Jun",
+    "Jul",
+    "Aug",
+    "Sep",
+    "Oct",
+    "Nov",
+    "Dec",
 ]
 PROJECT_ADJECTIVES = [
+    "Real-time",
+    "Scalable",
+    "Distributed",
+    "Cloud-native",
+    "AI-powered",
+    "Automated",
+    "Interactive",
+    "Cross-platform",
+    "Open-source",
+    "End-to-end",
+    "High-performance",
+    "Serverless",
+    "Event-driven",
+    "Microservice-based",
+    "Full-stack",
 ]
 PROJECT_NOUNS = [
+    "Dashboard",
+    "Platform",
+    "Pipeline",
+    "Application",
+    "System",
+    "API",
+    "Framework",
+    "Tool",
+    "Service",
+    "Engine",
+    "Chatbot",
+    "Recommendation System",
+    "Search Engine",
+    "Analytics Platform",
+    "Monitoring System",
+    "Marketplace",
 ]
 IMPACT_METRICS = [
 ]
 PHONE_AREA_CODES = [
+    "415",
+    "650",
+    "408",
+    "510",
+    "212",
+    "646",
+    "718",
+    "206",
+    "512",
+    "617",
+    "312",
+    "213",
+    "303",
+    "503",
+    "404",
+    "202",
 ]
 LINKEDIN_PREFIXES = [
+    "linkedin.com/in/",
+    "www.linkedin.com/in/",
 ]
 GITHUB_PREFIXES = [
+    "github.com/",
+    "www.github.com/",
 ]
 DOMAINS = [
+    "gmail.com",
+    "outlook.com",
+    "yahoo.com",
+    "protonmail.com",
+    "icloud.com",
+    "hotmail.com",
+    "mail.com",
 ]
 # ---------------------------------------------------------------------------
 # ---------------------------------------------------------------------------
 SYNONYMS = {
+    "developed": [
+        "built",
+        "created",
+        "engineered",
+        "designed",
+        "implemented",
+        "constructed",
+        "authored",
+    ],
+    "managed": [
+        "led",
+        "oversaw",
+        "directed",
+        "supervised",
+        "coordinated",
+        "administered",
+    ],
+    "improved": [
+        "enhanced",
+        "optimized",
+        "upgraded",
+        "refined",
+        "boosted",
+        "strengthened",
+    ],
+    "implemented": [
+        "deployed",
+        "executed",
+        "delivered",
+        "rolled out",
+        "launched",
+        "shipped",
+    ],
+    "analyzed": [
+        "examined",
+        "evaluated",
+        "assessed",
+        "investigated",
+        "studied",
+        "reviewed",
+    ],
+    "collaborated": [
+        "partnered",
+        "worked closely with",
+        "teamed up with",
+        "cooperated with",
+    ],
     "responsible for": ["in charge of", "accountable for", "tasked with", "owned"],
     "utilized": ["leveraged", "employed", "used", "applied", "harnessed"],
     "achieved": ["accomplished", "attained", "reached", "secured", "delivered"],
 # Helper utilities
 # ---------------------------------------------------------------------------
 def _pick(pool, k=1):
     """Return k unique random items from a pool."""
     k = min(k, len(pool))
             if w[0].isupper():
                 replacement = replacement.capitalize()
             # Preserve trailing punctuation
+            trailing = w[len(lower) :]
             result.append(replacement + trailing)
         else:
             result.append(w)
 # Section generators – each returns a string of realistic text
 # ---------------------------------------------------------------------------
 def generate_education() -> str:
     """Generate a realistic education section."""
     templates = []
         # Optional coursework
         if random.random() < 0.5:
+            courses = _pick(
+                MAJORS
+                + [
+                    "Algorithms",
+                    "Data Structures",
+                    "Operating Systems",
+                    "Database Systems",
+                    "Computer Networks",
+                    "Linear Algebra",
+                    "Probability and Statistics",
+                    "Deep Learning",
+                    "Natural Language Processing",
+                    "Computer Vision",
+                    "Distributed Systems",
+                ],
+                k=random.randint(3, 6),
+            )
+            prefix = random.choice(
+                ["Relevant Coursework:", "Key Courses:", "Coursework:"]
+            )
             lines.append(f"{prefix} {', '.join(courses)}")
         # Optional honors
         if random.random() < 0.3:
+            honor = random.choice(
+                [
+                    "Summa Cum Laude",
+                    "Magna Cum Laude",
+                    "Cum Laude",
+                    "Dean's List (all semesters)",
+                    "Honors Program",
+                    "University Scholar",
+                ]
+            )
             lines.append(honor)
         # Optional thesis
         if "Ph.D." in deg_short or ("M.S." in deg_short and random.random() < 0.4):
+            topic = random.choice(
+                [
+                    "Transformer-based approaches to document classification",
+                    "Scalable distributed systems for real-time data processing",
+                    "Graph neural networks for molecular property prediction",
+                    "Federated learning in healthcare applications",
+                    "Efficient attention mechanisms for long-sequence modeling",
+                    "Reinforcement learning for autonomous navigation",
+                ]
+            )
             label = "Dissertation" if "Ph.D." in deg_short else "Thesis"
+            lines.append(f'{label}: "{topic}"')
         return "\n".join(lines)
             deg_full, deg_short = _pick_one(DEGREES)
             major = _pick_one(MAJORS)
             year = _pick_one(GRAD_YEARS)
+            gpa_line = (
+                f" | GPA: {_pick_one(GPA_VALUES)}" if random.random() < 0.5 else ""
+            )
             entries.append(f"{deg_short} in {major}, {uni}, {year}{gpa_line}")
         return "\n".join(entries)
         year = _pick_one(GRAD_YEARS)
         lines = [f"{uni}", f"{deg_full} in {major} | {_pick_one(MONTHS)} {year}"]
+        activities = random.sample(
+            [
+                "Teaching Assistant for Introduction to Computer Science",
+                "President, Computer Science Student Association",
+                "Member, ACM Student Chapter",
+                "Undergraduate Research Assistant, ML Lab",
+                "Peer Tutor, Mathematics Department",
+                "Captain, University Programming Competition Team",
+                "Volunteer, Engineering Outreach Program",
+                "Member, Honors College",
+                "Study Abroad Program, Technical University of Munich",
+                "Resident Advisor, Engineering Living-Learning Community",
+            ],
+            k=random.randint(1, 3),
+        )
         b = _bullet()
         for a in activities:
         # Generate bullet points
         bullet_templates = [
+            f"Developed and maintained {random.choice(['microservices', 'APIs', 'web applications', 'data pipelines', 'ML models', 'backend systems', 'frontend components'])} using {', '.join(_pick(PROGRAMMING_LANGUAGES, k=random.randint(1, 3)))} and {', '.join(_pick(FRAMEWORKS, k=random.randint(1, 2)))}",
+            f"Collaborated with cross-functional teams of {random.randint(3, 15)} engineers to deliver {random.choice(['product features', 'platform improvements', 'system migrations', 'infrastructure upgrades'])} on schedule",
             f"Designed and implemented {random.choice(['CI/CD pipelines', 'testing frameworks', 'monitoring solutions', 'data models', 'caching strategies', 'authentication systems'])} that {_impact()}",
             f"Led migration of {random.choice(['legacy monolith', 'on-premise infrastructure', 'batch processing system', 'manual workflows'])} to {random.choice(['cloud-native architecture', 'microservices', 'real-time streaming', 'automated pipelines'])}",
+            f"Mentored {random.randint(2, 8)} junior engineers through code reviews, pair programming, and technical design sessions",
             f"Optimized {random.choice(['database queries', 'API response times', 'model inference', 'data processing pipelines', 'search indexing'])} resulting in {_impact()}",
             f"Wrote comprehensive technical documentation and {random.choice(['RFCs', 'design docs', 'runbooks', 'architecture decision records'])} for {random.choice(['system design', 'API contracts', 'deployment procedures', 'incident response'])}",
             f"Built {random.choice(['real-time', 'batch', 'streaming', 'event-driven'])} {random.choice(['data pipeline', 'ETL process', 'analytics system', 'feature store'])} processing {random.choice(['1M+', '10M+', '100M+', '1B+'])} records {random.choice(['daily', 'per hour', 'in real-time'])}",
         ]
         n_bullets = random.randint(2, 5)
+        selected = random.sample(
+            bullet_templates, min(n_bullets, len(bullet_templates))
+        )
         selected = _reorder_bullets(selected)
         b = _bullet()
         for bullet in selected:
         if random.random() < 0.9:
             fws = _pick(FRAMEWORKS, k=random.randint(3, 7))
+            label = random.choice(
+                ["Frameworks", "Frameworks & Libraries", "Technologies"]
+            )
             categories.append((label, fws))
         if random.random() < 0.8:
         return "\n".join(lines)
     def _t_flat():
+        all_skills = (
+            _pick(PROGRAMMING_LANGUAGES, k=random.randint(3, 6))
+            + _pick(FRAMEWORKS, k=random.randint(3, 6))
+            + _pick(TOOLS, k=random.randint(2, 4))
+        )
         random.shuffle(all_skills)
         joiner = random.choice([", ", " | ", " · ", " • "])
         return joiner.join(all_skills)
         levels = ["Expert", "Advanced", "Proficient", "Intermediate", "Familiar"]
         used = set()
         for level in random.sample(levels, k=random.randint(2, 4)):
+            pool = [
+                s for s in PROGRAMMING_LANGUAGES + FRAMEWORKS + TOOLS if s not in used
+            ]
             items = _pick(pool, k=random.randint(2, 5))
             used.update(items)
             lines.append(f"{level}: {', '.join(items)}")
 def generate_summary() -> str:
     """Generate a realistic professional summary / objective section."""
     years = random.randint(2, 15)
+    specialties = _pick(
+        MAJORS
+        + [
+            "full-stack development",
+            "distributed systems",
+            "machine learning",
+            "data engineering",
+            "cloud architecture",
+            "mobile development",
+            "DevOps",
+            "backend development",
+            "frontend development",
+            "natural language processing",
+            "computer vision",
+        ],
+        k=random.randint(1, 3),
+    )
     templates = [
         # Template 1: Traditional summary
+        lambda: (
+            f"Results-driven {_pick_one(JOB_TITLES).lower()} with {years}+ years of experience in {' and '.join(specialties)}. Proven track record of {random.choice(['delivering high-impact solutions', 'building scalable systems', 'driving technical excellence', 'leading cross-functional teams'])} at companies like {_pick_one(COMPANIES)} and {_pick_one(COMPANIES)}. Passionate about {random.choice(['clean code', 'system design', 'open source', 'mentorship', 'continuous learning', 'innovation'])} and {random.choice(['building products that scale', 'solving complex problems', 'leveraging data-driven insights', 'improving developer experience'])}."
+        ),
         # Template 2: Technical focus
+        lambda: (
+            f"Experienced {_pick_one(JOB_TITLES).lower()} specializing in {', '.join(specialties)}. Skilled in {', '.join(_pick(PROGRAMMING_LANGUAGES, k=3))} with deep expertise in {', '.join(_pick(FRAMEWORKS, k=2))}. {random.choice(['Strong background in', 'Demonstrated ability in', 'Track record of'])} {random.choice(['building distributed systems at scale', 'developing ML models for production', 'architecting cloud-native applications', 'leading agile engineering teams'])}. Seeking to {random.choice(['contribute to cutting-edge products', 'drive technical innovation', 'solve challenging problems', 'build impactful technology'])} at a {random.choice(['fast-growing startup', 'leading technology company', 'mission-driven organization'])}."
+        ),
         # Template 3: Achievement-oriented
+        lambda: (
+            f"{_pick_one(JOB_TITLES)} with {years} years of experience building {random.choice(['enterprise-scale', 'consumer-facing', 'B2B', 'data-intensive'])} applications. Key achievements include {_impact()}, {_impact()}, and {_impact()}. Proficient in {', '.join(_pick(PROGRAMMING_LANGUAGES, k=3))} and {', '.join(_pick(FRAMEWORKS, k=2))}."
+        ),
         # Template 4: Brief objective
+        lambda: (
+            f"Motivated {random.choice(['professional', 'engineer', 'developer', 'technologist'])} seeking a {_pick_one(JOB_TITLES).lower()} role where I can apply my expertise in {' and '.join(specialties)} to {random.choice(['build innovative products', 'solve real-world problems', 'drive business impact', 'push the boundaries of technology'])}."
+        ),
         # Template 5: Narrative style
+        lambda: (
+            f"I am a {_pick_one(JOB_TITLES).lower()} who thrives at the intersection of {_pick_one(specialties)} and {_pick_one(specialties)}. Over the past {years} years, I have {random.choice(['shipped products used by millions', 'built ML systems processing petabytes of data', 'led engineering teams through rapid growth', 'contributed to open-source projects with thousands of stars'])}. I bring a {random.choice(['data-driven', 'user-centric', 'systems-thinking', 'first-principles'])} approach to every problem I tackle."
+        ),
     ]
     return random.choice(templates)()
             f"{cert} ({year})",
             f"{cert} — Issued {_pick_one(MONTHS)} {year}",
             f"{cert}, {year}",
+            f"{cert}\n  Issued: {_pick_one(MONTHS_SHORT)} {year}"
+            + (
                 f" | Expires: {_pick_one(MONTHS_SHORT)} {year + random.randint(2, 3)}"
+                if random.random() < 0.3
+                else ""
             ),
         ]
         lines.append(random.choice(styles))
     last = _pick_one(LAST_NAMES)
     city = _pick_one(CITIES)
     area_code = _pick_one(PHONE_AREA_CODES)
+    email_user = random.choice(
+        [
+            f"{first.lower()}.{last.lower()}",
+            f"{first.lower()}{last.lower()}",
+            f"{first[0].lower()}{last.lower()}",
+            f"{first.lower()}_{last.lower()}",
+            f"{first.lower()}{random.randint(1, 99)}",
+        ]
+    )
     email = f"{email_user}@{_pick_one(DOMAINS)}"
+    phone = f"({area_code}) {random.randint(100, 999)}-{random.randint(1000, 9999)}"
     linkedin_user = f"{first.lower()}-{last.lower()}-{random.randint(100, 999)}"
     github_user = f"{first.lower()}{last.lower()}"
     if random.random() < 0.4:
         parts.append(f"{_pick_one(GITHUB_PREFIXES)}{github_user}")
     if random.random() < 0.2:
+        parts.append(
+            f"{github_user}.dev"
+            if random.random() < 0.5
+            else f"{first.lower()}{last.lower()}.com"
+        )
     sep = random.choice(["\n", " | ", " · ", "\n"])
     return sep.join(parts)
     for award in awards:
         year = random.randint(2015, 2025)
+        org = random.choice(
+            [
+                _pick_one(UNIVERSITIES),
+                _pick_one(COMPANIES),
+                random.choice(
+                    [
+                        "ACM",
+                        "IEEE",
+                        "Google",
+                        "Facebook",
+                        "Microsoft",
+                        "National Science Foundation",
+                        "Department of Education",
+                    ]
+                ),
+            ]
+        )
         styles = [
             f"{award}, {org} ({year})",
             f"{award} — {org}, {year}",
 # ---------------------------------------------------------------------------
 SECTION_HEADERS = {
+    "education": [
+        "EDUCATION",
+        "Education",
+        "Academic Background",
+        "ACADEMIC BACKGROUND",
+        "Education & Training",
+    ],
+    "experience": [
+        "EXPERIENCE",
+        "Experience",
+        "WORK EXPERIENCE",
+        "Work Experience",
+        "PROFESSIONAL EXPERIENCE",
+        "Professional Experience",
+        "Employment History",
+    ],
+    "skills": [
+        "SKILLS",
+        "Skills",
+        "TECHNICAL SKILLS",
+        "Technical Skills",
+        "Core Competencies",
+        "CORE COMPETENCIES",
+        "Technologies",
+    ],
+    "projects": [
+        "PROJECTS",
+        "Projects",
+        "PERSONAL PROJECTS",
+        "Personal Projects",
+        "SIDE PROJECTS",
+        "Selected Projects",
+        "Portfolio",
+    ],
+    "summary": [
+        "SUMMARY",
+        "Summary",
+        "PROFESSIONAL SUMMARY",
+        "Professional Summary",
+        "OBJECTIVE",
+        "Objective",
+        "PROFILE",
+        "Profile",
+        "About Me",
+        "ABOUT",
+    ],
+    "certifications": [
+        "CERTIFICATIONS",
+        "Certifications",
+        "CERTIFICATES",
+        "Certificates",
+        "Licenses & Certifications",
+        "PROFESSIONAL CERTIFICATIONS",
+    ],
+    "contact": [
+        "CONTACT",
+        "Contact",
+        "CONTACT INFORMATION",
+        "Contact Information",
+        "Personal Information",
+    ],
+    "awards": [
+        "AWARDS",
+        "Awards",
+        "HONORS & AWARDS",
+        "Honors & Awards",
+        "ACHIEVEMENTS",
+        "Achievements",
+        "Awards & Honors",
+        "RECOGNITION",
+    ],
 }
 GENERATORS = {
 # Dataset generation
 # ---------------------------------------------------------------------------
+def generate_example(
+    label: str, include_header: bool = False, augment: bool = False
+) -> str:
     """
     Generate a single synthetic example for the given label.
             # Generate augmented versions
             for _ in range(augmented_copies):
+                aug_text = generate_example(
+                    label, include_header=include_header, augment=True
+                )
                 dataset.append({"text": aug_text, "label": label})
     random.shuffle(dataset)
     # 80/10/10 split, stratified at both steps
     train_test = ds.train_test_split(test_size=0.2, seed=42, stratify_by_column="label")
+    val_test = train_test["test"].train_test_split(
+        test_size=0.5, seed=42, stratify_by_column="label"
+    )
     # Decode ids back to names. Casting ClassLabel -> string does NOT do this
     # (it stringifies the ids, giving "0"/"1"), and mapping into a column that
         "validation": val_test["train"],
         "test": val_test["test"],
     }
+    return DatasetDict(
+        {
+            name: split.map(to_label_name, batched=True, features=string_features)
+            for name, split in splits.items()
+        }
+    )
 def get_label_mapping(dataset: list[dict]) -> tuple[dict, dict]:
 if __name__ == "__main__":
     import argparse
+    parser = argparse.ArgumentParser(
+        description="Generate synthetic resume section data"
+    )
+    parser.add_argument(
+        "--examples-per-category",
+        type=int,
+        default=80,
+        help="Number of base examples per category (default: 80)",
+    )
+    parser.add_argument(
+        "--augmented-copies",
+        type=int,
+        default=2,
+        help="Number of augmented copies per example (default: 2)",
+    )
+    parser.add_argument(
+        "--output",
+        type=str,
+        default="data/resume_sections.csv",
+        help="Output CSV path (default: data/resume_sections.csv)",
+    )
+    parser.add_argument(
+        "--seed", type=int, default=42, help="Random seed (default: 42)"
+    )
+    parser.add_argument(
+        "--print-stats", action="store_true", help="Print dataset statistics"
+    )
+    parser.add_argument(
+        "--print-samples", type=int, default=0, help="Print N sample examples"
+    )
     args = parser.parse_args()
+    print(
+        f"Generating dataset with {args.examples_per_category} base examples per category..."
+    )
     print(f"Augmented copies per example: {args.augmented_copies}")
+    print(
+        f"Total expected examples: {args.examples_per_category * (1 + args.augmented_copies) * 8}"
+    )
     dataset = generate_dataset(
         examples_per_category=args.examples_per_category,
     if args.print_stats:
         from collections import Counter
         counts = Counter(d["label"] for d in dataset)
         print("\nDataset Statistics:")
         print(f"  Total examples: {len(dataset)}")
         print(f"  Average text length: {avg_len:.0f} chars")
     if args.print_samples > 0:
+        print(f"\n{'=' * 60}")
         print(f"Sample Examples (first {args.print_samples}):")
+        print(f"{'=' * 60}")
+        for i, example in enumerate(dataset[: args.print_samples]):
+            print(f"\n--- Example {i + 1} [{example['label']}] ---")
             print(example["text"][:300])
             if len(example["text"]) > 300:
                 print("...")

inference.py CHANGED Viewed

@@ -39,9 +39,11 @@ from transformers import AutoModelForSequenceClassification, AutoTokenizer
 # Data classes
 # ---------------------------------------------------------------------------
 @dataclass
 class SectionPrediction:
     """A single section classification result."""
     text: str
     label: str
     confidence: float
@@ -59,6 +61,7 @@ class SectionPrediction:
 @dataclass
 class ResumeAnalysis:
     """Complete resume analysis output."""
     sections: list
     section_count: int = 0
     label_distribution: dict = field(default_factory=dict)
@@ -114,7 +117,9 @@ SECTION_HEADER_PATTERNS = [
     r"ACTIVITIES|LEADERSHIP|RESEARCH)\s*:?\s*$",
 ]
-COMPILED_HEADERS = [re.compile(p, re.MULTILINE | re.IGNORECASE) for p in SECTION_HEADER_PATTERNS]
 def is_section_header(line: str) -> bool:
@@ -196,6 +201,7 @@ def split_resume_into_sections(text: str, min_section_length: int = 20) -> list:
 # Classifier
 # ---------------------------------------------------------------------------
 class ResumeSectionClassifier:
     """
     Classifies resume text sections into categories.
@@ -313,17 +319,21 @@ class ResumeSectionClassifier:
         results = []
         for i, text in enumerate(texts):
-            scores = {self.id2label[j]: probs[i][j].item() for j in range(probs.shape[1])}
             predicted_id = probs[i].argmax().item()
             predicted_label = self.id2label[predicted_id]
             confidence = probs[i][predicted_id].item()
-            results.append(SectionPrediction(
-                text=text,
-                label=predicted_label,
-                confidence=confidence,
-                all_scores=scores,
-            ))
         return results
@@ -361,6 +371,7 @@ class ResumeSectionClassifier:
 # CLI
 # ---------------------------------------------------------------------------
 def main():
     import argparse
@@ -380,18 +391,42 @@ Examples:
     input_group.add_argument("--file", type=str, help="Path to resume text file")
     input_group.add_argument("--text", type=str, help="Direct text to classify")
-    parser.add_argument("--model", type=str, default="./model_output/final_model",
-                        help="Path to fine-tuned model (default: ./model_output/final_model)")
-    parser.add_argument("--device", type=str, default=None,
-                        help="Device: cpu, cuda, mps (auto-detected if omitted)")
-    parser.add_argument("--max-length", type=int, default=256,
-                        help="Maximum token sequence length (default: 256)")
-    parser.add_argument("--min-section-length", type=int, default=20,
-                        help="Minimum section length in characters (default: 20)")
-    parser.add_argument("--format", type=str, choices=["text", "json"], default="text",
-                        help="Output format (default: text)")
-    parser.add_argument("--single", action="store_true",
-                        help="Classify as single section (no splitting)")
     args = parser.parse_args()
@@ -430,7 +465,9 @@ Examples:
                 bar = "#" * int(score * 40)
                 print(f"  {label:20s} {score:.4f} {bar}")
     else:
-        analysis = classifier.classify_resume(text, min_section_length=args.min_section_length)
         if args.format == "json":
             print(analysis.to_json())
         else:

 # Data classes
 # ---------------------------------------------------------------------------
 @dataclass
 class SectionPrediction:
     """A single section classification result."""
     text: str
     label: str
     confidence: float
 @dataclass
 class ResumeAnalysis:
     """Complete resume analysis output."""
     sections: list
     section_count: int = 0
     label_distribution: dict = field(default_factory=dict)
     r"ACTIVITIES|LEADERSHIP|RESEARCH)\s*:?\s*$",
 ]
+COMPILED_HEADERS = [
+    re.compile(p, re.MULTILINE | re.IGNORECASE) for p in SECTION_HEADER_PATTERNS
+]
 def is_section_header(line: str) -> bool:
 # Classifier
 # ---------------------------------------------------------------------------
 class ResumeSectionClassifier:
     """
     Classifies resume text sections into categories.
         results = []
         for i, text in enumerate(texts):
+            scores = {
+                self.id2label[j]: probs[i][j].item() for j in range(probs.shape[1])
+            }
             predicted_id = probs[i].argmax().item()
             predicted_label = self.id2label[predicted_id]
             confidence = probs[i][predicted_id].item()
+            results.append(
+                SectionPrediction(
+                    text=text,
+                    label=predicted_label,
+                    confidence=confidence,
+                    all_scores=scores,
+                )
+            )
         return results
 # CLI
 # ---------------------------------------------------------------------------
 def main():
     import argparse
     input_group.add_argument("--file", type=str, help="Path to resume text file")
     input_group.add_argument("--text", type=str, help="Direct text to classify")
+    parser.add_argument(
+        "--model",
+        type=str,
+        default="./model_output/final_model",
+        help="Path to fine-tuned model (default: ./model_output/final_model)",
+    )
+    parser.add_argument(
+        "--device",
+        type=str,
+        default=None,
+        help="Device: cpu, cuda, mps (auto-detected if omitted)",
+    )
+    parser.add_argument(
+        "--max-length",
+        type=int,
+        default=256,
+        help="Maximum token sequence length (default: 256)",
+    )
+    parser.add_argument(
+        "--min-section-length",
+        type=int,
+        default=20,
+        help="Minimum section length in characters (default: 20)",
+    )
+    parser.add_argument(
+        "--format",
+        type=str,
+        choices=["text", "json"],
+        default="text",
+        help="Output format (default: text)",
+    )
+    parser.add_argument(
+        "--single",
+        action="store_true",
+        help="Classify as single section (no splitting)",
+    )
     args = parser.parse_args()
                 bar = "#" * int(score * 40)
                 print(f"  {label:20s} {score:.4f} {bar}")
     else:
+        analysis = classifier.classify_resume(
+            text, min_section_length=args.min_section_length
+        )
         if args.format == "json":
             print(analysis.to_json())
         else:

train.py CHANGED Viewed

@@ -69,10 +69,18 @@ def build_compute_metrics(id2label: dict):
         predictions = np.argmax(logits, axis=-1)
         acc = accuracy_metric.compute(predictions=predictions, references=labels)
-        f1_macro = f1_metric.compute(predictions=predictions, references=labels, average="macro")
-        f1_weighted = f1_metric.compute(predictions=predictions, references=labels, average="weighted")
-        precision = precision_metric.compute(predictions=predictions, references=labels, average="weighted")
-        recall = recall_metric.compute(predictions=predictions, references=labels, average="weighted")
         return {
             "accuracy": acc["accuracy"],
@@ -88,7 +96,9 @@ def build_compute_metrics(id2label: dict):
 # ---------------------------------------------------------------------------
 # Tokenization
 # ---------------------------------------------------------------------------
-def tokenize_dataset(dataset_dict: DatasetDict, tokenizer, label2id: dict, max_length: int = MAX_LENGTH):
     """Tokenize all splits and encode labels as integers."""
     def preprocess(examples):
@@ -166,7 +176,9 @@ def train(
     logger.info(f"Model: {model_name}")
     logger.info(f"Output: {output_dir}")
     logger.info(f"Epochs: {epochs}, Batch size: {batch_size}, LR: {learning_rate}")
-    logger.info(f"Device: {'CUDA' if torch.cuda.is_available() else 'MPS' if torch.backends.mps.is_available() else 'CPU'}")
     logger.info(f"FP16: {fp16}")
     # ------------------------------------------------------------------
@@ -209,7 +221,9 @@ def train(
         label2id=label2id,
     )
     logger.info(f"  Parameters: {sum(p.numel() for p in model.parameters()):,}")
-    logger.info(f"  Trainable: {sum(p.numel() for p in model.parameters() if p.requires_grad):,}")
     # ------------------------------------------------------------------
     # 4. Training
@@ -253,7 +267,9 @@ def train(
     callbacks = []
     if early_stopping_patience > 0:
-        callbacks.append(EarlyStoppingCallback(early_stopping_patience=early_stopping_patience))
     trainer = Trainer(
         model=model,
@@ -281,7 +297,9 @@ def train(
     logger.info("\nTest Results:")
     for key, value in test_results.items():
-        logger.info(f"  {key}: {value:.4f}" if isinstance(value, float) else f"  {key}: {value}")
     # ------------------------------------------------------------------
     # Save artifacts
@@ -365,48 +383,92 @@ if __name__ == "__main__":
     )
     # Model & output
-    parser.add_argument("--model-name", type=str, default=MODEL_NAME,
-                        help="Pretrained model name or path")
-    parser.add_argument("--output-dir", type=str, default=DEFAULT_OUTPUT_DIR,
-                        help="Output directory for model and artifacts")
     # Training hyperparameters
-    parser.add_argument("--epochs", type=int, default=4,
-                        help="Number of training epochs")
-    parser.add_argument("--batch-size", type=int, default=16,
-                        help="Training batch size per device")
-    parser.add_argument("--learning-rate", type=float, default=2e-5,
-                        help="Peak learning rate")
-    parser.add_argument("--weight-decay", type=float, default=0.01,
-                        help="Weight decay for AdamW")
-    parser.add_argument("--warmup-ratio", type=float, default=0.1,
-                        help="Fraction of total steps for linear warmup")
-    parser.add_argument("--max-length", type=int, default=MAX_LENGTH,
-                        help="Maximum token sequence length")
-    parser.add_argument("--gradient-accumulation-steps", type=int, default=1,
-                        help="Number of gradient accumulation steps")
     # Data
-    parser.add_argument("--examples-per-category", type=int, default=80,
-                        help="Base synthetic examples per category")
-    parser.add_argument("--augmented-copies", type=int, default=2,
-                        help="Augmented copies per base example")
-    parser.add_argument("--seed", type=int, default=42,
-                        help="Random seed for reproducibility")
     # Training config
-    parser.add_argument("--fp16", action="store_true", default=None,
-                        help="Force FP16 training")
-    parser.add_argument("--no-fp16", action="store_true",
-                        help="Disable FP16 training")
-    parser.add_argument("--early-stopping-patience", type=int, default=3,
-                        help="Early stopping patience (0 to disable)")
     # Hub
-    parser.add_argument("--push-to-hub", action="store_true",
-                        help="Push trained model to HuggingFace Hub")
-    parser.add_argument("--hub-model-id", type=str, default=HUB_MODEL_ID,
-                        help="HuggingFace Hub model ID")
     args = parser.parse_args()

         predictions = np.argmax(logits, axis=-1)
         acc = accuracy_metric.compute(predictions=predictions, references=labels)
+        f1_macro = f1_metric.compute(
+            predictions=predictions, references=labels, average="macro"
+        )
+        f1_weighted = f1_metric.compute(
+            predictions=predictions, references=labels, average="weighted"
+        )
+        precision = precision_metric.compute(
+            predictions=predictions, references=labels, average="weighted"
+        )
+        recall = recall_metric.compute(
+            predictions=predictions, references=labels, average="weighted"
+        )
         return {
             "accuracy": acc["accuracy"],
 # ---------------------------------------------------------------------------
 # Tokenization
 # ---------------------------------------------------------------------------
+def tokenize_dataset(
+    dataset_dict: DatasetDict, tokenizer, label2id: dict, max_length: int = MAX_LENGTH
+):
     """Tokenize all splits and encode labels as integers."""
     def preprocess(examples):
     logger.info(f"Model: {model_name}")
     logger.info(f"Output: {output_dir}")
     logger.info(f"Epochs: {epochs}, Batch size: {batch_size}, LR: {learning_rate}")
+    logger.info(
+        f"Device: {'CUDA' if torch.cuda.is_available() else 'MPS' if torch.backends.mps.is_available() else 'CPU'}"
+    )
     logger.info(f"FP16: {fp16}")
     # ------------------------------------------------------------------
         label2id=label2id,
     )
     logger.info(f"  Parameters: {sum(p.numel() for p in model.parameters()):,}")
+    logger.info(
+        f"  Trainable: {sum(p.numel() for p in model.parameters() if p.requires_grad):,}"
+    )
     # ------------------------------------------------------------------
     # 4. Training
     callbacks = []
     if early_stopping_patience > 0:
+        callbacks.append(
+            EarlyStoppingCallback(early_stopping_patience=early_stopping_patience)
+        )
     trainer = Trainer(
         model=model,
     logger.info("\nTest Results:")
     for key, value in test_results.items():
+        logger.info(
+            f"  {key}: {value:.4f}" if isinstance(value, float) else f"  {key}: {value}"
+        )
     # ------------------------------------------------------------------
     # Save artifacts
     )
     # Model & output
+    parser.add_argument(
+        "--model-name",
+        type=str,
+        default=MODEL_NAME,
+        help="Pretrained model name or path",
+    )
+    parser.add_argument(
+        "--output-dir",
+        type=str,
+        default=DEFAULT_OUTPUT_DIR,
+        help="Output directory for model and artifacts",
+    )
     # Training hyperparameters
+    parser.add_argument(
+        "--epochs", type=int, default=4, help="Number of training epochs"
+    )
+    parser.add_argument(
+        "--batch-size", type=int, default=16, help="Training batch size per device"
+    )
+    parser.add_argument(
+        "--learning-rate", type=float, default=2e-5, help="Peak learning rate"
+    )
+    parser.add_argument(
+        "--weight-decay", type=float, default=0.01, help="Weight decay for AdamW"
+    )
+    parser.add_argument(
+        "--warmup-ratio",
+        type=float,
+        default=0.1,
+        help="Fraction of total steps for linear warmup",
+    )
+    parser.add_argument(
+        "--max-length",
+        type=int,
+        default=MAX_LENGTH,
+        help="Maximum token sequence length",
+    )
+    parser.add_argument(
+        "--gradient-accumulation-steps",
+        type=int,
+        default=1,
+        help="Number of gradient accumulation steps",
+    )
     # Data
+    parser.add_argument(
+        "--examples-per-category",
+        type=int,
+        default=80,
+        help="Base synthetic examples per category",
+    )
+    parser.add_argument(
+        "--augmented-copies",
+        type=int,
+        default=2,
+        help="Augmented copies per base example",
+    )
+    parser.add_argument(
+        "--seed", type=int, default=42, help="Random seed for reproducibility"
+    )
     # Training config
+    parser.add_argument(
+        "--fp16", action="store_true", default=None, help="Force FP16 training"
+    )
+    parser.add_argument("--no-fp16", action="store_true", help="Disable FP16 training")
+    parser.add_argument(
+        "--early-stopping-patience",
+        type=int,
+        default=3,
+        help="Early stopping patience (0 to disable)",
+    )
     # Hub
+    parser.add_argument(
+        "--push-to-hub",
+        action="store_true",
+        help="Push trained model to HuggingFace Hub",
+    )
+    parser.add_argument(
+        "--hub-model-id",
+        type=str,
+        default=HUB_MODEL_ID,
+        help="HuggingFace Hub model ID",
+    )
     args = parser.parse_args()