Blind / README.md
debugdll's picture
Update README.md
7b966be verified
|
Raw
History Blame Contribute Delete
756 Bytes
metadata
license: apache-2.0
tags:
  - text-generation
  - transformers
  - russian
  - llm
  - from-scratch
  - pytorch

Blind - LLMs, trained from scratch

A series of models from 1 to 3B parameters, created entirely from scratch and trained on Russian-language data.

A project for enthusiasts, students, and developers who want to experiment with LLMs without a huge investment.


Models

File Size Parameters
blind_one_param_model.pt 3 KB 1
blind-0-ultrasmall.pt 173 MB ~50M
blind-0-small.pt 356 MB ~85M
blind-0-medium.pt 407 MB ~100M
blind-0-large.pt 445 MB ~110M
blind-1.pt 1 GB ~740M
blind-1.1.pt 1 GB ~750M
blind-1.5.pt 6 GB ~3B