# Low Resource Requirements

Bonsai is a small ternary-weighted language model with 500 million parameters, built on the Llama architecture and using the Mistral tokenizer, trained on fewer than 5 billion tokens.

A small speech recognition model based on the OpenAI Whisper architecture, focused on English speech-to-text tasks.

MythoMax L2 13b is a large language model based on the Q4_K_M quantized version, suitable for text generation tasks.

TinyLlama is a 1.1B parameter Llama model, planned to be pretrained on 3 trillion tokens, optimized to complete training in 90 days on 16 A100-40G GPUs.

A Russian Q&A model fine-tuned from cointegrated/rubert-tiny2, suitable for SQuAD-format question answering tasks

A lightweight text sentiment classification model based on DistilBERT, fine-tuned on the emotion dataset

A lightweight model fine-tuned on the NER task based on the DistilBERT-base-uncased model