|
--- |
|
language: |
|
- en |
|
- ru |
|
license: apache-2.0 |
|
|
|
|
|
tags: |
|
- gpt |
|
- NLG |
|
|
|
--- |
|
# HuYaLM 100B |
|
|
|
**Hu**gging Face **YaLM 100B** (by [BlackSamorez](https://github.com/BlackSamorez)) is a **transformers-compatible** implementation of the **YaLM 100B** model. Originally trained by Yandex, the model used 800 A100 graphics cards and 1.7 TB of diverse text data, including online texts and books, in both English and Russian. |
|
|
|
The motivation behind this particular implementation is to update the originally published, outdated code to align with the latest advancements in the field. As this code is compatible with the _transformers_ library, it inherently supports crucial features like [quantization](https://huggingface.co/docs/transformers/main_classes/quantization) (for model size optimization) and [adapter training](https://huggingface.co/docs/peft/index) (for efficient fine-tuning). |
|
|
|
For more details on training, acceleration, and stabilization techniques, you can refer to articles on **[Medium](https://medium.com/p/d1df53d0e9a6)** (in English) and **[Habr](https://habr.com/ru/company/yandex/blog/672396/)** (in Russian). The original code from Yandex is available on [GitHub](https://github.com/yandex/YaLM-100B). |
|
|
|
This code and model are distributed under the [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) license, which allows for commercial use. |
