Note checkout their chat space: https://huggingface.co/spaces/01-ai/Yi-34B-Chat

Note checkout olmo suite: https://huggingface.co/collections/allenai/olmo-suite-65aeaae8fe5b6b2122b46778

Note checkout datatrove: https://github.com/huggingface/datatrove (freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.)

Note read more: https://fasttext.cc/

Note checkout: https://github.com/huggingface/nanotron (minimalistic large language model 3D-parallelism training)

Note from creators of grok: https://huggingface.co/xai-org/grok-1

Note checkout transformers compatible mambas: https://huggingface.co/collections/state-spaces/transformers-compatible-mamba-65e7b40ab87e5297e45ae406

Note checkout https://huggingface.co/docs/trl (train transformer language models with reinforcement learning.)

Note checkout https://github.com/huggingface/alignment-handbook (robust recipes to align language models with human and AI preferences)

Note read more: https://huggingface.co/blog/gptq-integration (Making LLMs lighter with AutoGPTQ and transformers)

Note read more: https://huggingface.co/docs/bitsandbytes (accessible large language models via k-bit quantization for PyTorch)

Note checkout lighteval: https://github.com/huggingface/lighteval (lightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron)