-
**描述这个 bug**
我想使用lstm训练wmt16-en-ro，我是把wmt16-ro-en的数据集的src和tgt互换得到的数据，在训练时发现bleu始终为0，打开generation.txt查看发现生成的全是乱码，在查看数据集发现数据集是正常的，但是生成出来的却是乱码
**如何复现**
run_textbox.py --model=lstm --num_layers=2 --e…
-
### Describe the feature
If I want to train t5 or mt5 model with my dataset,whether it can be implemented using Colossal AI ?
-
## Issue description
Some LLMs are currently part of the `popular_on_huggingface` corpus of MLAgility. Those models are significantly large, causing our benchmarking infrastructure to take signific…
-
If you haven’t already, check out our [contributing guidelines](https://github.com/Expensify/ReactNativeChat/blob/main/contributingGuides/CONTRIBUTING.md) for onboarding and email contributors@expensi…
-
These are models that support a wider range of languages.
- mT5 https://huggingface.co/docs/transformers/model_doc/mt5
- mBART https://huggingface.co/docs/transformers/model_doc/mbart
- NLLB http…
-
hi , on mt5 when panel is minimized switching timeframe causes a quick flash(panel become visible for a second).
-
### Describe the bug
There's a bug in the `neptune/internal/utils/paths.py` file (line 26). If an int object is provided, this line causes an error.
The easy work-around is to add call to `str`:
``…
-
我想用T5、GPT把英文翻译成中文
-
First of all, I would like to thank you for making the code for work available and I also say that I really liked your paper. It is very interesting.
I am currently writing my master's thesis and I…
-
I'm very impressed by SPLADE, particularly the newest efficient versions. However, it is only trained on English texts.
There's an [mMARCO dataset](https://github.com/unicamp-dl/mMARCO) that has 1…