---

base_model: LiquidAI/LFM2.5-1.2B-Instruct

language:

- en

license: other

pipeline_tag: text-generation

tags:

- gguf

- llama.cpp

- hiring

- tanpo

- text-generation

---

Tanpo Hiring (GGUF)

GGUF quantizations of d4rkninja/tanpo-hiring for local runtimes (llama.cpp, LM Studio, and other GGUF-compatible tools).

Creator: d4rkninja

Collection: Tanpo — Domain Specialists

Original upstream: LiquidAI/LFM2.5-1.2B-Instruct (~1.17B parameters, 32,768-token context, designed for edge/on-device deployment).

Fine-tuning: Unsloth-compatible loading of that checkpoint via hub id unsloth/LFM2.5-1.2B-Instruct (LoRA / PEFT).

A compact hiring / talent specialist (~1.2B) for JDs, scorecards, screens, interview loops, and offer framing — built for local and inexpensive deployment.

Available quantizations

Sizes from the Hugging Face file API (approximate on-disk):

| File | Size |

|---|---:|

| tanpo-hiring.Q3_K_M.gguf | 573 MB |

| tanpo-hiring.Q4_K_M.gguf | 697 MB |

| tanpo-hiring.Q4_K_S.gguf | 668 MB |

| tanpo-hiring.Q5_K_M.gguf | 804 MB |

| tanpo-hiring.Q5_K_S.gguf | 787 MB |

| tanpo-hiring.Q8_0.gguf | 1189 MB |

Suggested everyday file: tanpo-hiring.Q4_K_M.gguf

Evaluation (summary)

| Model | Rubric overall |

|---|---:|

| Base | 83.8% |

| Fine-tune | 92.9% |

| Delta | +9.2 percentage points |

Full methodology on the merged model card. Artifacts: evaluation/. Quantization can change behavior slightly vs BF16 merged weights.

Running locally

1. Download tanpo-hiring.Q4_K_M.gguf (or another quant above).
2. Open it in LM Studio or run with llama.cpp (use a build that supports LFM2 / the model architecture).
3. Keep prompts in the hiring domain; review consequential outputs with a human.

No separate LoRA step is required — these are standalone GGUF files of the merged specialist.

Related

• Merged Transformers: d4rkninja/tanpo-hiring
• LoRA: d4rkninja/tanpo-hiring-LoRA

Responsible Use

Always keep humans in the loop for screening, debriefs, and offers. Avoid biased criteria; comply with applicable employment law. Do not use for unauthorized access to candidate data or systems.

License

license: other — this repository inherits obligations from the upstream Liquid AI LFM2.5 / LFM family base model (LiquidAI/LFM2.5-1.2B-Instruct; training hub id unsloth/LFM2.5-1.2B-Instruct). Review Liquid AI’s license terms before commercial redistribution or redistribution of derivatives. Do not assume Apache-2.0 covers the merged weights.

Tanpo Model Family

Tanpo is a family of small, domain-specialized business models for local / edge / inexpensive deployment — not frontier or general-purpose models. Strength comes from specialization for specific business workflows.

| Domain | Merged | LoRA | GGUF |

|---|---|---|---|

| Marketing | tanpo-marketing | tanpo-marketing-LoRA | tanpo-marketing-GGUF |

| Product | tanpo-product | tanpo-product-LoRA | tanpo-product-GGUF |

| Hiring | tanpo-hiring | tanpo-hiring-LoRA | tanpo-hiring-GGUF |

| Deals | tanpo-deals | tanpo-deals-LoRA | tanpo-deals-GGUF |

Original upstream: LiquidAI/LFM2.5-1.2B-Instruct (~1.17B, 32K context)
  └── Unsloth-compatible hub load: unsloth/LFM2.5-1.2B-Instruct
        └── Tanpo Specialist (domain SFT via LoRA)
              ├── Full / Merged  → d4rkninja/tanpo-hiring
              ├── LoRA adapter   → d4rkninja/tanpo-hiring-LoRA
              └── GGUF quants    → d4rkninja/tanpo-hiring-GGUF