Fact-checking and judges

Atla Selene

An 8B judge model: it scores another model answer against your criteria and writes a rationale. The judge itself makes mistakes and does not replace manual review on important tasks.

Developer
Atla, UK
First release
Jan 2025
Latest release
Jan 2025
Sizes
8B
License
Commercial use with conditionsThe card states Apache 2.0; the model is fine-tuned from Llama 3.1 — check the base license terms
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Software development, Customer support, Science and research, Marketing and content
Deploy on your server Hugging Face

What it does

  • Scoring chatbot answers against your own criteria
  • Comparing two versions of a prompt or model
  • Filtering out weak answers before they reach a person

Where it is used

IT and software developmentCustomer supportMarketing and content

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
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Selene-1-Mini-Llama-3.1-8B

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 Atla Selene be used in a commercial project?

With conditions. License: The card states Apache 2.0; the model is fine-tuned from Llama 3.1 — check the base license terms. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Atla Selene need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Atla Selene support Russian?

No. The developer documentation lists the supported languages and Russian is not among them.

Where can I download Atla Selene and what does it cost?

The Atla Selene 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

Fact-checking and judgesPrometheus 2KAIST and LG AI Research (prometheus-eval) · South KoreaCommercial use allowed

An open judge model: it scores other models' answers against your criteria and explains the score. A replacement for paid models in the reviewer role.

DetailsFact-checking and judgesFlow JudgeFlow AI · not disclosedCommercial use allowed

A small judge model: it checks an answer against your instruction and gives a score with an explanation. Fits on a modest server. The judge itself makes mistakes and does not replace manual review.

DetailsFact-checking and judgesGLIDER (Patronus)Patronus AI · USANon-commercial only

A small judge: it scores against your criteria and highlights which part of the answer led to that score. The license is non-commercial. The judge itself makes mistakes and does not replace manual review.

Details

Source: huggingface.co/AtlaAI/Selene-1-Mini-Llama-3.1-8B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.