唐国梁Tommy

FinGPT-v1 , errors with download_titles.py

2

I don't understand what does `al_re` mean ? ```python # ATTENTION! Should replace this with your results path! al_re = os.listdir(r"D:\python_project\FinRL-Meta\experiment\scrape\results") al_re = [al.split(".")[0] for al in al_re] ```

Hello, Sorry to ask you that : when I run your code : python3 lanenet/train.py --dataset ./data/training_data_example I got the answer : 10 epochs 4 training samples Epoch 0 Best...

微调后的模型格式转换为 Xtuner / HF / LLaVA 的问题

1

## 问题-1 你好，当我运行脚本`llava_llama3_8b_instruct_qlora_clip_vit_large_p14_336_e1_gpu1_finetune.py`后，对保存后的模型进行格式转换，`.pth` --> `xtuner`格式，文件结构如下： 这个模型结构与开源的模型文件结构不同，这是为什么？ **xtuner/llava-llama-3-8b-v1_1** 结构如下： ## 问题-2 如果将基于 QLoRA方式微调后的模型转换为 huggingface 格式，会抛出异常信息如下： ``` self.to_huggingface_llava(cfg, save_dir, fp32, File "/root/autodl-tmp/xtuner/xtuner/model/llava.py", line 420, in to_huggingface_llava assert getattr(self.llm, 'hf_quantizer', None) is None,...