foreveronehundred
foreveronehundred
Fix the following bug. TypeError: 'type' object is not subscriptable
As title, I found that the content of llama-Xb-hf/tokenizer_config.json is like the following, ``` {"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LLaMATokenizer", "unk_token": ""} ``` How did your team modify...
For translation quality estimation of COMET, I think there is no limitation of the text length. However, from my personal perspective, I do not think the estimation will be accurate...
Hi, Could you add torch.onnx.export() in tools/export-onnx.py. Currently in tools/export-onnx.py, it only does inference.