Cunxiao Du

[MODEL] add 2 new text classification models

2

## Description ## add two models (region embedding ICLR 2018 and exam AAAI 2019) for text classification. ## Checklist ## ### Essentials ### - [x] PR's title starts with a...

smn 是有分词的

1

给的数据都是分好词的，他说的word level应该就是中文里面的词级别

what are the train/val/test split of JDDC in your experiment

5

Hi, Thanks for your nice work, and I got jddc corpus from the original author. But the dataset only contains these columns "session_id user_id role sku content intent". So I...

…se.py code style ## 📌 Checklist before creating the PR - [ ] I have created an issue for this PR for traceability - [ ] The title follows the...

非常感谢

bfloat16 of fused attention seems have bug

3

both [fused-attention](https://triton-lang.org/main/getting-started/tutorials/06-fused-attention.html#sphx-glr-getting-started-tutorials-06-fused-attention-py) and [flash-attn-og](https://github.com/Dao-AILab/flash-attention/blob/main/flash_attn/flash_attn_triton_og.py) cannot pass the bfloat16 test

The update of k_cache_paged and v_cache_paged

1

Hi tspeterkim, Thanks for your great code! I am wondering why the v_cache_paged and k_cache_paged is not updated.

[Bug]: No output after input text

1

### Is there an existing issue for the same bug? - [X] I have checked the existing issues. ### Describe the bug and reproduction steps After I launch the docker...