simplew2011
simplew2011
- https://hf-mirror.com/facebook/fasttext-zh-vectors - https://hf-mirror.com/facebook/fasttext-en-vectors can not find zh model in https://zenodo.org/records/4905385
Reference link [11342](https://github.com/open-mmlab/mmdetection/issues/11342) implemented TensorRT deployment, found that the accuracy of fp32/fp16 cannot be aligned with the accuracy under onnx
not found FastTextQualityFilter model weight file, how to download it.
- Is it okay not to shuffle the data? ``` def _exact_dup_ids(self, df: dd.DataFrame): """ Get the id's for text/documents that are exact duplicates Parameters ---------- df: dask.dataframe.core.DataFrame A dataframe...
can you release a cpu veriosn in fuzzy dedup
### Description of the bug | 错误描述 - service已启动 - client报错     ### How to reproduce the bug | 如何复现 ``` cd projects/multi_gpu python service.py python client.py...
### Prerequisite - [x] I have searched [Issues](https://github.com/open-compass/opencompass/issues/) and [Discussions](https://github.com/open-compass/opencompass/discussions) but cannot get the expected help. - [x] The bug has not been fixed in the [latest version](https://github.com/open-compass/opencompass). ### Type...
- 当前Qwen2VLChat方式只支持本地加载方式 - LMDeployAPI方式不支持Qwen2-VL-7B-Instruct
- 是否支持超长seq_len(16/32k)onnx导出、simply简化及推理
- 能否作为一个pypi库发布 - 【Predefined Task Set】,设置100,【待处理指令数据集】的每个样本都需要前向推理100次,速度较慢;有没有实验设置10个是不是能达到精度要求 - 【Predefined Task Set】是否一定要从【待处理指令数据集】里选取 - 示例参数里`--prompt_path "datasets/alpaca_gpt4/alpaca_gpt4_data.json" --test_path "datasets/alpaca_gpt4/alpaca_gpt4_kmeans_100.json"`,【待处理指令数据集】被定义为prompt_path,【Predefined Task Set】被定义为test_path,交换一下参数定义是不是更好理解 - [tasks/alpaca.py#L81](https://github.com/pldlgb/nuggets/blob/master/tasks/alpaca.py#L81),这里prefix为什么为空呢 - 默认参数跑,为什么win_rate和norm_win_rate的值是一样的