xcxhy

Training model save problem

10

### Describe the feature Hello, I use the ChatGPT/examples/train_dummpy.py to train GPT2, and the training is successful, but the trained model cannot be found. Can you write a document to...

How to use your own dataset to train and fine-tune the VQA task of BLIP2-flant5xl

24

Hi, thank you very much for open source. I want to use my own Image and caption, and QA data to fine-tune the BLIP2 data. Should my process be to...

The Problem on blip2_feature_extraction Example

1

Hello author, in the example/blip2_feature_ectraction.ipynb file, it seems that is not no blip2_feature_extractor model file mentioned in your code. I can't find the model in the model zoo, should I...

add an example for text retrieval

1

hello, Use BLIP to encode each picture and description, and then use text to encode some keywords, and recall words related to pictures and texts from keywords.

Support Multi-gpus inference on 3090s

1

Hi, I can successfully infer with a single 3090, but setting tensor_parallel_size=2 throws the following error: Traceback (most recent call last): File "test_batch.py", line 78, in llm = LLM(model=args.model_path, tensor_parallel_size=2)...

script.js文件中修改了97后前四张图还是loading占位

3

我根据你的说的修改了script.js文件中的97行后，每篇博客的前四张图片点开还是loading占位图，但是剩下的图片正常，有什么解决方法吗？ 我测试了一下，是由于isSPA设置为true的时候，preloadRatio默认为1时，由于我第一张图就在正面就不会懒加载，这时就会导致fancybox点不了该图片。 目前解决了，把暴露在首页的图片设置nolazy才可以解决，有别的解决方法吗

[Usage] Problems with using models

2

### Describe the issue When I ran the second step, I entered the downloaded `llava_plus_v0_7b` model path in advance, which brought the following error, can you tell me where the...

convert Onnx problem

11

Hi, thanks for your open source. I would like to ask why the llama-7b model I converted using torch.onnx.export is not the same as the model published on your hugging...