Update README.md

README.md

@@ -8,13 +8,11 @@ pipeline_tag: text-generation
 
 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 (on identical russian text sequences!) with HF because of different tokenizer.
 
-Paper: Tikhomirov M., Chernyshev D. Impact of Tokenization on LLaMa Russian Adaptation //arXiv preprint arXiv:2312.02598. – 2023.
+rccmsu/ruadapt_mistral_7b_v0.1 trained on saiga corpuses.
+The quality is slightly worse than the IlyaGusev/saiga_mistral_7b_lora, but faster because of tokenizer.
 
-## Training procedure
+WARNING! Load tokenizer as AutoTokenizer.from_pretrained(model_path, use_fast=True)
 
-ruadapt mistral trained on saiga corpuses.
-The quality is slightly worse than the IlyaGusev/saiga_mistral_7b_lora, but faster because of tokenizer.
+Paper: Tikhomirov M., Chernyshev D. Impact of Tokenization on LLaMa Russian Adaptation //arXiv preprint arXiv:2312.02598. – 2023.