Use in the same way as IlyaGusev/saiga2_7b_lora.

Up to 60% faster generation and 35% training (on identical russian text sequences!) with HF because of different tokenizer.

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.

WARNING! Load tokenizer as AutoTokenizer.from_pretrained(model_path, use_fast=True)

Paper: Tikhomirov M., Chernyshev D. Impact of Tokenization on LLaMa Russian Adaptation //arXiv preprint arXiv:2312.02598. – 2023.

Downloads last month
10
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.