Text Generation
Transformers
PyTorch
llama
text-generation-inference
WizardLM-70B-V1.0 / tokenizer_config.json

Commit History

  1. Maximum sequence length for a Llama 2 model is 4096 (#3)⁠

    WizardLM +1: TheBloke
    153924a

  1. 70B V1.0

    37558d7