Text analysisText

ESCOXLM-R и JobBERT (ITU Copenhagen)

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.

The last open version came out in Nov 2023. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
Mike Zhang, Rob van der Goot, Barbara Plank (IT University of Copenhagen and LMU Munich), Denmark
First release
Apr 2022
Latest release
Nov 2023
Sizes
110M – 560M
License
Commercial use with conditionsApache 2.0 for ESCOXLM-R; the early JobBERT and JobSpanBERT models state no license on their cards
Russian
Not stated
Running
On your own serverAlso runs without a GPU
Industries
HR, Education, Public sector
Deploy on your server Hugging Face GitHub

What it does

  • Extracting skills and requirements from vacancy text
  • Mapping skills to the single ESCO reference list
  • Classifying vacancies and job titles
  • Labour market analytics

Where it is used

HR and recruitingJob boardsLabour market research

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. ESCOXLM-R skill и knowledge extraction
  2. ESCOXLM-R на базе XLM-R large
  3. JobBERT skill и knowledge extraction
  4. JobBERTa
  5. JobBERT и JobSpanBERT

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can ESCOXLM-R и JobBERT (ITU Copenhagen) be used in a commercial project?

With conditions. License: Apache 2.0 for ESCOXLM-R; the early JobBERT and JobSpanBERT models state no license on their cards. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does ESCOXLM-R и JobBERT (ITU Copenhagen) need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does ESCOXLM-R и JobBERT (ITU Copenhagen) support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download ESCOXLM-R и JobBERT (ITU Copenhagen) and what does it cost?

The ESCOXLM-R и JobBERT (ITU Copenhagen) weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Search and RAGJobBERT (TechWolf)TechWolf · BelgiumCommercial use allowed

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.

DetailsSearch and RAGConTeXT-Skill-ExtractionTechWolf · BelgiumCommercial use with conditions

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.

DetailsText analysisGLiNERUrchade Zaratiana and Fastino AI · France / USACommercial use allowed

Finds the entities you need in text without training: just list what to look for (name, amount, date). GLiNER2 also classifies text. Multilingual versions understand Russian.

Details

Source: huggingface.co/jjzha/esco-xlm-roberta-large. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.