Simone Riggi

Dear @jiajunlong, thanks for the reply. Yes, I use lora fine tuning in both the first and second epoch model. I have added '_lora.' in the model path directory, but...

Just wanted to add that the `adapter_config.json` files produced in the nepoch1 and 2 paths are different. In the latter, there are layers with subfix ".base_layer" or "lora_A.default". I attach...

Dear @jiajunlong, yes the model path passed to ~load_pretrained_model` is "/scratch/riggi/Analysis/MLProjects/TinyLLaVA/fine-tuning/radioimg-dataset/TinyLLaVA-Phi-2-SigLIP-3.1B/vision_freeze/nepochs2/_lora". From the logs (attached below) it seems the code is indeed executing the `elif model_name_or_path is not None and...

@eva10084 Initially, I loaded the model from huggingface `tinyllava/TinyLLaVA-Phi-2-SigLIP-3.1B` as: ``` deepspeed custom_finetune.py \ --pretrained_model_path tinyllava/TinyLLaVA-Phi-2-SigLIP-3.1B --output_dir $SAVED_MODEL_PATH [OTHER OPTIONS] ``` The model files for `tinyllava/TinyLLaVA-Phi-2-SigLIP-3.1B` are automatically downloaded if...

Same error while trying the HF demo (https://huggingface.co/OpenGVLab/InternVL2-40B) on 4 GPU server (python3.10, transformers v4.43.2): ``` device_map {'language_model.model.layers.0': 0, 'language_model.model.layers.1': 0, 'language_model.model.layers.2': 0, 'language_model.model.layers.3': 0, 'language_model.model.layers.4': 0, 'language_model.model.layers.5': 0, 'language_model.model.layers.6':...

I have fixed the missing keys issue when loading the model using the suggestion reported in this post: #270. Basically, the original model weights have layers prefixed as "detector." while...

Hi @MohammedAdelFahmi, if I increase the confidence threshold to 0.5, I do not get any detections, as the scores of the 200 detected objects are in the range [0,0.03]. If...