Single GPU DeepSpeed, download model without loading to RAM

What's Changed

• DeepSpeed on single GPU by @BobaZooba in #8
• Add project_name by @BobaZooba in #11
• set transformers version by @BobaZooba in #12
• Download model without loading to RAM by @BobaZooba in #13

Full Changelog: 0.1.7...0.1.8

Tokenizer hotfix

What's Changed

• Tokenizer trust remote code by @BobaZooba in #2

Int8 fusing

What's Changed

• Int8 fusing by @BobaZooba in #1

Full Changelog: 0.1.1...0.1.2

Stable release

🎉 Code and documents done!

Useful materials

• Quickstart: basics of xllm
• Examples: minimal examples of using xllm
• Guide: here, we go into detail about everything the library can
  do
• Demo project: here's a minimal step-by-step example of how to use X—LLM and fit it
  into your own project
• WeatherGPT: this repository features an example of how to utilize the xllm library. Included is a solution for a common type of assessment given to LLM engineers, who typically earn between $120,000 to $140,000 annually
• Shurale: project with the finetuned 7B Mistal model

Init Release

Code done and tested. Time to docs