xmc-andy

Some weights of OtterForConditionalGeneration were not initialized from the model

23

Hello, I encountered such an output when testing the trained weights. I spent a long time trying to find out the reason. Unfortunately, I haven't found out the cause of...

About choosing dataset format and pre-training weights

2

Hello, authors! I have a question about choosing a dataset format and corresponding weights. I am doing a classification task with multiple images and prompt input. If multiple images are...

Checkpoint update?

2

Hello, authors, I noticed that you updated the checkpoint of OTTER-Image-MPT7B about a month ago. My checkpoint date is still in August. Is there any update?

Is it correct to set up fsdp for a machine (V100) that does not support bf16?

6

compute_environment: LOCAL_MACHINE distributed_type: no downcast_bf16: false machine_rank: 0 main_training_function: main mixed_precision: fp16 num_machines: 1 num_processes: 1 rdzv_backend: static same_network: true tpu_use_cluster: false tpu_use_sudo: false use_cpu: false main_process_port: 20687