In HR, open models parse resumes, match candidates to roles, answer employee questions about internal policies and support training. Self-hosting matters because resumes and employee records are personal data. Check quality in your languages and the license, and keep decisions about people with a human.
T-Bank models fine-tuned from Qwen for Russian: they write and reason in Russian noticeably better than the original. T-Lite is 8B, T-Pro 32B on one GPU; T-Search is a multi-step search agent in Russian and English.
A fine-tuned Qwen3-VL-8B reads resume pages as images and returns a 23-field JSON record. The author states plainly that the model is not meant for automated decisions about candidates; a human decides.
The most widely used open tool for splitting a recording by speaker: who spoke and when. Usually paired with speech recognition. Weights are issued after a short form on HF.
A model from a Belgian HR company: it turns job titles into vectors so you can find similar vacancies and resumes. A human makes the decision about a candidate; automatic screening without review must not be used.
A recent open AI-text detector on DeBERTa-v3-large, trained on the RAID dataset, with a separate version for academic work. It errs in both directions - a human always reviews the result.
A German-language model that matches a resume to occupations from the European ESCO reference list and suggests suitable directions. A human makes the decision about a candidate; automatic screening without review must not be used.
Finds mentions of skills in a vacancy or resume text and maps them to the company skill reference list. A human makes the decision about a candidate; automatic screening without review must not be used.
Turns a scanned page into tagged text with block coordinates, or into markdown. Handy as the first step before parsing a resume. A human makes the decision about a candidate; automatic screening without review must not be used.
Turns a free-form occupation description into a standard HISCO code in 13 languages. Built for historical archives, but also useful for cleaning up job title reference lists. A human makes the decision about a candidate; automatic screening without review must not be used.
One model for every document task: reading, answering questions about a page, extracting fields, classification. In HR it is used to parse resumes and attached scans. A human makes the decision about a candidate; automatic screening without review must not be used.
One of the first open AI-text classifiers, trained on the HC3 corpus of paired human and ChatGPT answers. It errs in both directions: its output is a reason to talk to the author, not proof.
A research line of models for labour market texts: trained on job postings and the European ESCO occupation taxonomy, they pull skills and requirements out of vacancies. A human makes the decision about a candidate; automatic screening without review must not be used.
Reads a document or a screenshot as an image and answers with structure: text, fields, answers to questions. In HR it is fine-tuned for resumes and forms. A human makes the decision about a candidate; automatic screening without review must not be used.
A light model that takes both the text and the position of blocks on the page into account: trained in one language and transferable to others. Good for tagging fields in resumes and forms. A human makes the decision about a candidate; automatic screening without review must not be used.
Reads a scanned document and returns a filled-in field structure straight away, with no separate OCR step. In HR it is fine-tuned for parsing resumes and forms. A human makes the decision about a candidate; automatic screening without review must not be used.
From an image it works out what kind of document it is: resume, diploma, certificate, contract. Helps sort candidate file bundles by type. A human makes the decision about a candidate; automatic screening without review must not be used.
Practically the only fully open weight set for single-frame face liveness: it tells a live person from a photo, a screen or a mask. It errs in both directions - a person must be able to appeal a rejection.
An open model can run on your own server: data stays in-house, there is no per-request fee, and the model can be fine-tuned on your documents.
