Linus Lin

got same issue.

I've run `make glove` and got error like... wget -P ./data/ "http://nlp.stanford.edu/data/glove.6B.zip" --2019-05-03 11:27:36-- http://nlp.stanford.edu/data/glove.6B.zip Resolving nlp.stanford.edu... 171.64.67.140 Connecting to nlp.stanford.edu|171.64.67.140|:80... connected. HTTP request sent, awaiting response... 302 Found Location:...

@freesunshine0316 Thank you for pointing out! My question is: Why the matching encoder output concatenated with `in_passage_repres` , instead of `cur_in_passage_repres`? here: `encode_hiddens = tf.concat([aggregation_representation, in_passage_repres], 2)` Because equation (3)...

Upgrading to `transformers==4.41.1` worked for me. Because starting from some versions, LLaMa architecture has been included for the Flax causal LMs class. [Here](https://github.com/huggingface/transformers/blob/75f15f39a0434fe7a61385c4677f2700542a7ba6/src/transformers/models/auto/modeling_flax_auto.py#L153) is the list of supported models.

> Thank you @bminixhofer , it is now working. Still the other script doesn't work > > ``` > scripts/transfer.py \ > --target_model=mistralai/Mistral-7B-v0.1 \ > --revision=refs/pr/95 \ > --tokenizer_name=EleutherAI/gpt-neox-20b \...