jinghanhu

How to customize a learning environment?

2

I'm a MARL learner. I want to customize a MARL learning environment based on macad-gym. How should I proceed?

Using Swift to perform inference and fine-tune InternVL-Chat-V1.5

15

Thanks for your awesome work. [swift](https://github.com/modelscope/swift) now supports inference, training of InternVL-Chat-V1.5 model For more information, please refer to our document - [English](https://github.com/modelscope/swift/tree/main/docs/source_en/Multi-Modal/internvl-best-practice.md) - [中文](https://github.com/modelscope/swift/blob/main/docs/source/Multi-Modal/internvl%E6%9C%80%E4%BD%B3%E5%AE%9E%E8%B7%B5.md) For more questions, please raise...

# PR type - [x] Bug Fix - [x] New Feature - [x] Document Updates - [ ] More Models or Datasets Support # PR information New quantization algorithms: -...

As mentioned in https://github.com/OpenGVLab/InternVL/issues/129 It is recommended to set the tokenizer's vocab_size to be a multiple of 32 (and consequently adjust the dimensions of the embedding and the final lm_head,...

# PR type - [ ] Bug Fix - [ ] New Feature - [ ] Document Updates - [x] More Models or Datasets Support # PR information https://github.com/modelscope/swift/issues/908

Qlora with eetq is quite slow

3

The training process is quite slow, whereas using 8-bit hqq speeds it up by more than tenfold. Is this normal? Or have I missed any code？ ```python import torch from...

# PR type - [ ] Bug Fix - [x] New Feature - [ ] Document Updates - [ ] More Models or Datasets Support

# PR type - [ ] Bug Fix - [ ] New Feature - [ ] Document Updates - [x] More Models or Datasets Support # PR information https://www.modelscope.cn/datasets/AI-ModelScope/ShareGPT4V/summary https://www.modelscope.cn/datasets/AI-ModelScope/LLaVA-Instruct-150K/summary...

# PR type - [ ] Bug Fix - [x] New Feature - [ ] Document Updates - [ ] More Models or Datasets Support # PR information [SimPO](https://arxiv.org/abs/2405.14734) TODO:...

# PR type - [ ] Bug Fix - [ ] New Feature - [ ] Document Updates - [x] More Models or Datasets Support # PR information Write the...