-
In this [Convert Vocabulary](https://ubiquitouslearning.github.io/mllm_website/customization/convert_vocabulary/) page, the shell script `python vocab.py --input_file=tokenizer.model --output_file=voc…
-
## 論文URL
https://arxiv.org/abs/2404.05225
## 著者
Chuwei Luo, Yufan Shen, Zhaoqing Zhu, Qi Zheng, Zhi Yu, Cong Yao
## 会議
CVPR 2024
## 背景
## 目的
## アプローチ
## ひとことメモ
-
-
Hello authors, thanks for this interesting work and for releasing the code.
I have setup a [colab notebook (GPT4)](https://colab.research.google.com/drive/1cGdfpqP8NYHWfPcwgAs3_Rq2l3MuUttM?usp=shar…
-
论文中提到,需要一个vision-to-decoder projector将所有的image feature变换到decoder的embedding_dim。
在SAM和LISA中,这是由nn.Conv2d单独完成的,out_chans直接就是decoder的embedding_dim 256。
而本文的image feature来自于MLLM的ViT输出,输出dim为1024。然后在…
-
On merging the PT Lora Adaptor to base model it increased the size to almost double to that of orig base model.
I am pre-training LLama2 for a non-Englist language.
For this i expanded Tokenizer v…
-
Fine-tuning alpha-clip LLaVA-1.5 is mentioned in paper 4.2. Alpha-CLIP in MLLM. I wonder the detail settings. Do you train the model just following stage 1, stage 2 in Paper GPT4ROI?
And if i want…
-
Using Windows 10 and I have CUDA version 12.3
The error occurs when I try to import Llama
FileNotFoundError: [WinError 3] The system cannot find the path specified: 'C:\\Program Files\\NVIDIA GPU Co…
-
the weights of SPHINX-MoE-1k you uploaded in hf can not be loaded correctly. This is the output log:
```
File "/data/mllm/project/LLaMA2-Accessory/accessory/demos/multi_turn_mm.py", line 66, in mode…
-
同样的推理代码,使用`internlm-xcomposer2-vl`时正常运行,但是使用`internlm-xcomposer-vl`会报bug。麻烦您帮忙看一下!
Error log:
```shell
2024-03-07 19:58:55,750 - modelscope - INFO - PyTorch version 2.0.1+cu117 Found.
2024-03-07…