metadata
library_name: peft
language:
- ru
Use in the same way as IlyaGusev/saiga2_7b_lora.
WARNING! Load tokenizer as AutoTokenizer.from_pretrained(model_path, use_fast=True)
Up to 60% faster generation and 35% training with HF because of different tokenizer.
Model description
Instruction version (Saiga datasets) of Russian adaptation of LLaMa-2-7B by replacing the tokenizer. Paper: Tikhomirov M.M., Chernyshev D.I., Impact of Tokenization on LLaMa Russian Adaptation (will be soon)