Seungwoo Kim comments

Results 3 comments of


                                            Seungwoo Kim

Adding upstage layout analysis for parsing documents such as html, pdf, jpg...

@JuHyung-Son Hi, I just found that Upstage's Document Parse is way better than any other tools. Is there any plan for or progress in incorporating Document Parse into Dify?

Failed to convert Qwen2-VL-7B-Instruct LORA model

If you don't want downgrading transformers, you should add `position_embeddings` to module_kwargs [transformers==4.47.1](https://github.com/huggingface/transformers/blob/241c04d36867259cdf11dbb4e9d9a60f9cb65ebc/src/transformers/models/qwen2_vl/modeling_qwen2_vl.py#L552-L559) [transformers==4.48.0](https://github.com/huggingface/transformers/blob/6bc0fbcfa7acb6ac4937e7456a76c2f7975fefec/src/transformers/models/qwen2_vl/modeling_qwen2_vl.py#L549)

"Clarification on Multimodal Model Quantization and Default Calibration Dataset"

Hi, @donghong1 1. As far as I know, AWQ itself quantizes only the language model, not vision encoders. I saw the paper proposed quantizing vision encoders but not sure which...