Hongrui Liu
Hongrui Liu
Why does the training set data contain facial landmarks? It seems that the facial landmarks are not used during the training process, just helps to crop the image?
I found that the retrieval rate is really high for Self-RAG. in active_pipeline.py line 164 judge_retrieve(self, input_prompts): ``` all_pred_text = [] all_pred_log_probs = [] # For vllm, requesting too many...
Can you provide the scripts for deploying the freebase and configuring the embedding for different datasets? Also, the requirement.txt still has problems.
The spec-infer works well for batch size (1,2,4,8,16). But I change the batch size to 32, it turns out to be "stack smashing detected" ```+ ncpus=16 + ngpus=1 + fsize=30000...