xliucs

some detail of gector-large

2

@MaksTarnavskyi I am interested in your paper “Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction” and I want to reproduce your results. However, I have some...

[Bug Report] Load model to mutilple devices

7

When I use the following code to load LLama2 and generate: ```python model = HookedTransformer.from_pretrained("meta-llama/Llama-2-7b-chat-hf", hf_model=hf_model, device="cuda", n_devices=4, move_to_device=True, fold_ln=False, center_writing_weights=False, center_unembed=False, tokenizer=tokenizer) model.generate("The capital of Germany is", max_new_tokens=20, temperature=0)...

phonetic预训练细节

8

论文里面说使用带错误的训练数据预训练phonetic Encoder， 但代码里面好像是用的纠正后的数据，不知道我有没有理解错，恳请解惑 

您好，我们对您的工作很感兴趣，想问一下在数据准备时，N个错误的句子重复N次这一步，您是人工做的还是自动化处理的呢？