Yam(长琴)

**pypi package need update** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior: ```bash /usr/local/lib/python3.8/site-packages/scairdt/date_time/base_date.py:8: in from recognizers_number.number import Constants as NumberConstants...

**Proto file(s)** List protocol buffer definitions ```proto service Extracting { rpc ExtractKeyWord (ExtractRequest) returns (ExtractKeyWordResponse) {} } message ExtractRequest { string text = 1; int32 topk = 2; } message...

fix sequence_mask with None lengths

2

the code location: `encoders/transformer.py`: ```python class TransformerEncoder(EncoderBase): ... def forward(self, src, lengths=None): """See :func:`EncoderBase.forward()`""" self._check_args(src, lengths) emb = self.embeddings(src) out = emb.transpose(0, 1).contiguous() mask = ~sequence_mask(lengths).unsqueeze(1) # Run the forward...

paddle 模式下词性标注，并发时可能会出错

7

错误代码在 `predict.py`： ```python def get_result(str1): feed_data=dataset.get_vars(str1) a = numpy.array(feed_data).astype(numpy.int64) a=a.reshape(-1,1) c = fluid.create_lod_tensor(a, [[a.shape[0]]], place) words, crf_decode = exe.run( infer_program, fetch_list=[infer_ret['words'], infer_ret['crf_decode']], feed={"words":c, }, return_numpy=False, use_program_cache=True) results=[] results += utils.parse_result(words,...

why the mask hstack in model.py?

2

Here is the code in model.py (line 482) ```python # When performing key-value caching, we compute the attention scores # only for the new sequence. Thus, the matrix of scores...

Poor quality when batch inferencing

1

code as below: ```python prompt1 = "Hey, how are you doing today?" prompt2 = "Hey, good." description = "A female speaker with a slightly low-pitched voice delivers her words quite...

Why need noisy train data?

5

Hello, i am confused by the code in line 241 of `style_transfer.py`: ``` get_batches(train0, train1, vocab.word2id, args.batch_size, noisy=True) ``` i have seen the `noise` function, it's mainly used to randomize...

llm-deploy

2

### 你是否已经阅读并同意《Datawhale开源项目指南》？ - [X] 我已阅读并同意[《Datawhale开源项目指南》](https://github.com/datawhalechina/DOPMC/blob/main/GUIDE.md) ### 你是否已经阅读并同意《Datawhale开源项目行为准则》？ - [X] 我已阅读并同意[《Datawhale开源项目行为准则》](https://github.com/datawhalechina/DOPMC/blob/main/CODE_OF_CONDUCT.md) ### 项目简介 关于模型/LLM推理和部署理论与实践。 ### 立项理由 1. 弥补推理和部署方面的缺乏。 2. 为更多对本领域感兴趣的同学或行业内外从业人员提供一个不错的入门资料。 ### 项目受众 1. 算法工程师。 2. 对推理部署感兴趣的同学。 ### 项目亮点 1. 推理部署相关理论与实践。 2....