sz2three

when I use `python3 -m fastchat.serve.cli --model-path mpt-7b --load-8bit ` , it causes this error `ValueError: Tokenizer class GPTNeoXTokenizer does not exist or is not currently imported.`

ConnectionError when launch the model worker(s)

1

when launch the model worker(s): `python3 -m fastchat.serve.model_worker --model-name 'vicuna-7b-v1.1' --model-path /path/to/vicuna/weights ` it has error as follows: `2023-05-30 17:19:25 | ERROR | stderr | ConnectionError: HTTPConnectionPool(host='localhost', port=21001): Max retries...

text2vec数据集构建

1

看huggingface的例子，[例子](https://huggingface.co/chestnutlzj/ChatLaw-Text2Vec#examples)， text2vec的原始数据看起来像QA问答的数据，请问您是怎么把问答数据构建成为文本embeddings训练的数据的呢，CoSENT的训练是不是需要 （sentence1,sentenc2,sentenc3） 三个样本呢？

How to set background image in training ?

3

I have two classes ( classA:1, classB:2) in my custom images. Now there are some other images without any bboxes, should I use these images as background images? And How...

when I run demo.py, I have set `--save_result` as True, but where is the annotations （labels or x, y, w,h values）of demo? I only find the detection image with bounding...

数据可商用吗

1

数据的license是什么

how to edit yolo label with imported txt labels ?

1

I have get the annotated yolo images and txt files. And I haved loaded data in notebook. How do I **only** `edit `bboxes without the need of pretrained models?

does it support Korea and Japanese?

1

it supports Chinese, while does it also work for Korea and Japanese?

when use ` python quant_infer.py --wbits 2 --load pyllama-7B8b.pt --text "..." --max_length 24 ` , it raises error `NVMLError_NoPermission: Insufficient Permissions`