d4rkninja/tanpo-hiring

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.2BQuant:BF16Context Size:32kPublished:Sep 17, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

d4rkninja/tanpo-hiring is a compact 1.2 billion parameter, 32,768-token context language model developed by d4rkninja, fine-tuned from LiquidAI/LFM2.5-1.2B-Instruct. This specialized model is optimized for various hiring and talent acquisition workflows, including generating job descriptions, scorecards, interview loops, and offer framing. It is designed for local and inexpensive deployment, excelling at structured recruiting artifacts.

Loading preview...

Tanpo Hiring: A Compact Domain Specialist for Talent Acquisition

Tanpo Hiring is a 1.2 billion parameter language model, fine-tuned by d4rkninja from the LiquidAI/LFM2.5-1.2B-Instruct base, specifically for human resources and recruiting tasks. Part of the "Tanpo — Domain Specialists" collection, this model is engineered for local and inexpensive deployment, making it suitable for edge or on-device applications.

Key Capabilities & Features

  • Specialized Workflow Support: Excels at generating structured content for the entire hiring lifecycle.
  • Compact & Efficient: At ~1.2B parameters with a 32,768-token context, it's designed for performance on resource-constrained environments.
  • Performance Improvement: Achieves a 9.2 percentage point improvement over its base model on internal automated domain evaluations for hiring tasks.
  • LoRA Fine-tuning: Utilizes LoRA (PEFT) via Unsloth for efficient adaptation, with merged weights provided.
  • Dedicated Dataset: Trained on d4rkninja/tanpo-hiring-sft, comprising ~10k format-fixed chat SFT examples.

Best For

  • Creating role-specific job descriptions and hiring scorecards.
  • Drafting outbound recruiting sequences and screening scripts.
  • Designing interview loops and structured interview kits.
  • Composing debrief calibration prompts, offer framing, and rejection drafts.

Limitations

As a specialized model, its quality may degrade outside the hiring workflow. It has limited world knowledge and long-horizon reasoning compared to larger, general-purpose models. Users must ensure human review for final decisions and compliance with employment law.

Finetunes
3 models