mindnlp

mindnlp copied to clipboard

**Describe the bug/ 问题描述 (Mandatory / 必填)** pipelines推理中document_question_answering.py示例 2，其中dqa_pipeline入参缺少image - **Hardware Environment(`Ascend`/`GPU`/`CPU`) / 硬件环境**: > Please delete the backend not involved / 请删除不涉及的后端: > /device ascend/GPU/CPU/ - **Software Environment /...

cui0523

fill_mask

1

添加了fill_mask的pipeline，目前ut存在tensor索引错误的问题 issue链接： https://gitee.com/mindspore/community/issues/I97UT8

QAQusers

**Describe the bug/ 问题描述 (Mandatory / 必填)** A clear and concise description of what the bug is. CLIPProcessor和CLIPScore处理图像后获得的feature与transforemers结果差距较大 - **Hardware Environment(`Ascend`/`GPU`/`CPU`) / 硬件环境**: > Please delete the backend not involved...

ChongWei905

BaseTunerLayer类的get_base_layer()方法循环调用导致Python对象时超过的最大递归深度。

2

**Describe the bug/ 问题描述 (Mandatory / 必填)** 在微调模型时候，出现了因为BaseTunerLayer类的get_base_layer()方法的循环引用，导致调用Python对象时超过的最大递归深度。 - **Hardware Environment(`Ascend`/`GPU`/`CPU`) / 硬件环境**:GPU > Please delete the backend not involved / 请删除不涉及的后端: > /device ascend/GPU/CPU/kirin/等其他芯片 - **Software Environment / 软件环境...

stringency

whisper-tiny无法输出简中

7

无法返回简中推理结果，使用以下代码： ```import time import mindspore as ms # 指定设备 ms.set_context(device_target="Ascend", device_id=1) from mindnlp.transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline model_id = "openai/whisper-tiny" model = AutoModelForSpeechSeq2Seq.from_pretrained( model_id, ms_dtype=ms.float16, low_cpu_mem_usage=True, use_safetensors=True, ) processor =...

yang-441

lvyufeng

lvyufeng

lvyufeng

**Is your feature request related to a problem? Please describe.** When using mindnlp to infer GPT2, I found that the inference speed is 10X slower than pytorch. Here is the...

WilliamLiuAtCPC

lvyufeng