Upload original model files

#2
by Yhyu13 - opened

When using Ooba, there needs not only quantized file but also orignal mode configs and tokenizer model

Could not load the model because the tokenizer files could not be found in the model folder. Please download the following files from the original (unquantized) model into models/Llama-2-13b-E8P-2Bit: special_tokens_map.json, tokenizer.json, tokenizer.model, tokenizer_config.json.

Sign up or log in to comment