-
When I try to run this command:
`python src/train.py -mode test_text -text_src data/sum_twitter_sample.txt -test_from bertext_cnndm_transformer.pt`
I get this error:
```
[2020-11-18 17:36:5…
-
## ❓ Questions and Help
Thanks for releasing the mbart models! Referring to [#1758 ](https://github.com/pytorch/fairseq/issues/1758) I reproduced the same results, which is basically close to the r…
-
But the processing is the same with I.1, and it should have files under 'data/wiki/txt', rather than 'data/wiki'.
The script is confusing.
```
# build the training set for BPE tokenization (50k cod…
-
@pjox and I are working on a model trained with Roberta and using the BPE tokenizer, in particular [zeldarose](https://github.com/LoicGrobol/zeldarose) which uses slightly different special tokens.
…
-
Hi @thinhlpg, I'm curious about how many epochs you fine-tuned the model to achieve this performance level
-
## Description
(A clear and concise description of what the bug is.)
When running distributed training (multi-instance with each instance having a single GPU) with sparse gradients (produced by nega…
-
Hi. Thanks for the open sourced models! This is a major step forward to the democratization of LLMs.
I'm trying to fine tune `openlm-research/open_llama_7b` using the LORA.
I first tried the cod…
-
### Description
Hi, I defined a multitask learning problem by fusion of PTB and IMDB for testing the mixing of different type of modality problems. But when the training goes to the line 444 of multi…
-
Preparing dialog data in /var/lib/tf_seq2seq_chatbot/data
Creating vocabulary /var/lib/tf_seq2seq_chatbot/data/vocab20000.in from data /var/lib/tf_seq2seq_chatbot/data/chat.in
Traceback (most recent…
-
Hi,
I have been trying to run the wmt demo on TPUv2 or TPUv3 VMs, but I keep encountering a `bac_alloc` error before training even starts. It seems that the output also says that no TPU backend is…