whatisgithub

What is yalm-100b?

yandex/yalm-100b — explained in plain English

Analysis updated 2026-06-26

3,756PythonAudience · researcherComplexity · 5/5LicenseSetup · hard

In one sentence

YaLM 100B is a 100-billion-parameter text-generation model from Yandex, released under Apache 2.0, that generates English and Russian text given a prompt, but running it requires serious multi-GPU hardware.

Mindmap

mindmap
  root((YaLM 100B))
    What it does
      Text generation
      Bilingual EN and RU
      100B parameters
    Setup
      Download 200GB weights
      Multi-GPU required
      Docker container
    Usage
      Interactive CLI
      Batch file input
      Free generation
    Training
      800 GPUs 65 days
      1.7TB text data
      DeepSpeed framework
    License
      Apache 2.0
      Commercial allowed
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Generate long-form Russian or English text from a prompt using a 100B-parameter open-weight model

USE CASE 2

Run batch conditional text generation from a file of input prompts using greedy or sampling decoding

USE CASE 3

Study Yandex's bilingual pre-training data pipeline and filtering methodology for large language models

USE CASE 4

Use the model as a research baseline for Russian-language NLP tasks that need a large open-weight model

What is it built with?

PythonDeepSpeedDockerShell

How does it compare?

yandex/yalm-100bnabla-c0d3/sslyzereinderien/mimic
Stars3,7563,7563,754
LanguagePythonPythonPython
Setup difficultyhardeasyeasy
Complexity5/52/52/5
Audienceresearcherops devopsdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · hard Time to first run · 1day+

Requires multiple high-end GPUs with ~200 GB total GPU memory and 200 GB disk space just to load the model weights.

Apache 2.0, use freely for any purpose including commercial, as long as you keep the copyright notice.

So what is it?

YaLM 100B is a large text-generating neural network built by Yandex and released for public use by developers and researchers. It works similarly to other GPT-style models: given some text as input, it predicts and outputs the next words. The model can handle both English and Russian, reflecting the bilingual makeup of the data it was trained on. Training this model was a significant undertaking. Yandex ran it on 800 high-end graphics cards for about 65 days, processing roughly 1.7 terabytes of text drawn from web pages, books, news, social media, and Wikipedia. About a quarter of that data came from an English dataset called The Pile, and the rest was Russian text carefully filtered and deduplicated to remove junk, repetitive content, and low-quality pages. Using the model requires serious hardware. The weights alone take up 200 gigabytes of disk space, and running inference requires multiple graphics cards totaling around 200 gigabytes of GPU memory. The repository includes shell scripts to download the weights, pull a pre-built Docker container, and start generating text without having to configure the environment from scratch. Once set up, you can interact with the model in several ways: type prompts directly from the command line for immediate responses, feed it a file of inputs for conditional generation using sampling or greedy decoding, or let it generate text freely without any prompt at all. Each mode corresponds to a ready-made example script in the repository. The code here is not the original training code. It is a lightly modified version of an example from the DeepSpeed project, adapted just enough to load and run Yandex's trained weights. The model weights and a companion vocabulary file are hosted on Hugging Face and can be downloaded via the included script or by cloning the Hugging Face repository directly. The model is released under the Apache 2.0 license, which allows both research and commercial use.

Copy-paste prompts

Prompt 1
Help me write a shell script to download the YaLM 100B weights from Hugging Face and start the Docker container for text generation.
Prompt 2
Show me how to run batch inference with yalm-100b from a file of prompts using the sampling script included in the repo.
Prompt 3
What are the exact GPU requirements to run inference with yalm-100b, and how should I split the model across multiple GPUs with DeepSpeed?
Prompt 4
I want to compare YaLM 100B's Russian text output to a newer model, help me write a Python evaluation script that feeds both the same prompts and compares outputs.

Frequently asked questions

What is yalm-100b?

YaLM 100B is a 100-billion-parameter text-generation model from Yandex, released under Apache 2.0, that generates English and Russian text given a prompt, but running it requires serious multi-GPU hardware.

What language is yalm-100b written in?

Mainly Python. The stack also includes Python, DeepSpeed, Docker.

What license does yalm-100b use?

Apache 2.0, use freely for any purpose including commercial, as long as you keep the copyright notice.

How hard is yalm-100b to set up?

Setup difficulty is rated hard, with roughly 1day+ to a first successful run.

Who is yalm-100b for?

Mainly researcher.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.